Osint MCP Server

Describe valid filters, groupings, metrics, detail fields, and citation fields for ai_infrastructure.construction.

Describe valid filters, groupings, metrics, detail fields, and citation fields for ai_infrastructure.employment.

Describe valid filters, groupings, metrics, detail fields, and citation fields for ai_infrastructure.equipment_trade.

Describe valid filters, groupings, metrics, detail fields, and citation fields for ai_infrastructure.production.

Describe valid filters, groupings, metrics, detail fields, and citation fields for ai_infrastructure.trade.

Describe any served capability by name — the generic twin of the named describe tools. Pass `capability` as either a capability id from list_capabilities_v1 (e.g. "power.capacity") or a query primitive name (e.g. "query_power_capacity_v1"). Returns the same schema payload as the named describe tool: valid filters, groupings, metrics, detail fields, and citation fields. Use the generic pair (this + query_capability_v1) when list_capabilities_v1 names a capability that has no named tool in your client's tool list — clients cache tool lists, and capabilities shipped after that cache are still fully reachable here.

Describe capacity factor: net generation / (operating nameplate × hours), joined across EIA-860M and EIA-923.

Describe the EIA Henry Hub and state electric-power gas-price atoms, units, aggregate grain, missingness, vintages, and citations.

Describe annual EIA-860 ownership filters, convention, metrics, and exact-cell citations.

Describe PJM ELCC document identities, class dimensions, metrics, and citations.

Describe PJM RPM delivery-year/LDA filters, UCAP metrics, and citations.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.capacity.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.demand_rollup.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.demand.

Describe EIA-923 receipt/cost filters, raw units, missing semantics, and exact-cell citations.

Describe valid filters, groupings, atoms, metrics, detail fields, and citation fields for power.generation.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.interconnection_queue_caiso.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.interconnection_queue_ercot.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.interconnection_queue_isone.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.interconnection_queue_nyiso.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.interconnection_queue_pjm_cycle.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.interconnection_queue_pjm.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.interconnection_queue_spp.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.interconnection_queue.

Describe native-XBRL Form 1 plant-cost facts, units, coverage, and exact-fact citations.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.price_ercot.

Describe valid filters, groupings, metrics, detail fields, and citation fields for power.retail_sales.

Describe valid filters, groupings, metrics, detail fields, and citation fields for robotics.adoption.

Describe valid filters, groupings, metrics, detail fields, and citation fields for robotics.trade.

Describe valid filters, groupings, metrics, detail fields, and citation fields for space.satellite_filings.

Query verified annual EIA-860 generator ownership. Returns the Owner schedule's raw owner names and ownership shares for each `eia_plant_id` + `generator_id`. `percent_owned` is the workbook's raw fraction of one (0.6 = 60%), not a whole-number percent. Filter by plant, generator, exact raw owner name, state, owner state, annual vintage, or source-reported balancing authority code; `{"state":"TX","balancing_authority_code":"ERCO"}` returns an ERCOT slice in one call. Owner-name matching is exact and intentionally performs no normalization or entity resolution. Critical EIA convention: the Owner schedule contains only jointly owned generators and generators wholly owned by an entity other than the operator. A generator absent from it is wholly owned by the operator in that same annual EIA-860 Generator schedule. An exact plant+generator query exposes this as `ownership_resolution`; it does not fabricate an Owner row or a 1.0 source share. Annual vintages remain independently queryable. Every returned share cites its exact ZIP member, sheet, row, and `Percent Owned` cell for SHA-256 verification.

Query cited PJM marginal ELCC class ratings by document kind, auction, delivery year, and resource class. Preliminary, final, and incremental-auction documents remain separate; no value is preferred or reconciled.

Query cited PJM Base Residual Auction UCAP clearing prices, RTO cleared MW, reliability requirement, and published administrative price collar by delivery year and LDA.

Query verified U.S. generator-level operating, planned, retired, or canceled power capacity from EIA-860M. Use this for capacity questions by state/jurisdiction, county FIPS, source-reported balancing authority code, fuel, prime mover, technology, lifecycle, or year. Pass filters inside the `params` object. The operating/planned/retired/canceled selector is `lifecycle` (e.g. `lifecycle: "operating"`, the default) — there is no `status` or `status_group` parameter. Returns JSON aggregates with citations and optional generator-level records when `include_records` is true. Does not determine electricity supplied, generation MWh, real-time dispatch, capacity factor, battery storage throughput/duration, demand/load, prices, data-center load, or transmission deliverability. For capacity REQUESTED in an ISO interconnection queue (projects pending interconnection, not yet built), use the relevant ISO's queue tool: query_power_interconnection_queue_v1 (MISO), query_power_interconnection_queue_pjm_v1 (PJM — or query_power_interconnection_queue_pjm_cycle_v1 for PJM's cluster/cycle grid), or query_power_interconnection_queue_caiso_v1 (CAISO).

Query verified U.S. hourly electricity demand (MW) as EIA's own published national and regional totals from the EIA Grid Monitor (region-data). Use this for "how much load for the whole country, or a region" questions. Filter by `respondent` (US48 = the Lower-48 national total, or one of the 13 EIA regions — CAL, CAR, CENT, FLA, MIDA, MIDW, NE, NW, NY, SE, SW, TEN, TEX), `data_date` (one day) or the `data_date_from`/`data_date_to` range, and `hour_number`. To pin one specific UTC hour, combine `data_date` + `hour_number`. Group by any of `respondent`, `respondent_level` (national vs region), `data_date`, `hour_number`, or `datetime_utc`. `datetime_utc` and `respondent_level` are grouping/output axes only — not filters. Pass each parameter as a top-level key of `params` (flat — not nested under a `filter`, `filters`, or `where` key). Example: `{"respondent": "US48", "data_date": "2026-06-10", "hour_number": 14}` for the US48 total at one hour; add `"group_by": ["datetime_utc"]` over a `data_date_from`/`data_date_to` range for a series. Returns JSON aggregates with citations and optional row-level records when `include_records` is true. `demand_mw` is EIA's OWN published demand total, served verbatim — the Adjusted series (the same canonical definition as power.demand's `demand_mw`), NOT a sum exascale computed. This closes power.demand's refusal of national/region totals (BA demand is non-additive across balancing authorities). `demand_forecast_mw` is the same respondent-hour's day-ahead forecast, so forecast-vs-actual misses need no second query. History runs hourly from 2019-01-01 onward — this published series begins about 3.5 years later than power.demand's balancing-authority history — and is served by default; the response `as_of` is the knowledge cut. A query with NO calendar window and no calendar-axis `group_by` defaults to the latest day with reported demand and says so in a `default_latest_day` note — group by `data_date` or `datetime_utc`, or pass a date range, for a series over time. Pin `as_of` to an earlier vintage to reproduce what was served then. INVERTED additivity: `demand_mw` is ALREADY a published total, so it is NOT additive across respondents — US48 already equals the sum of the 13 regions. A result spanning more than one respondent without grouping by it carries a `respondent_aggregation` scope note and ranking remainders omit the demand metrics: filter `respondent=US48` for the national total, or group by `respondent` for the per-respondent series. Occasional source-quality anomalies (an hour EIA did not publish; a rare impossible value EIA published) are served verbatim and cited, never altered. Does not determine balancing-authority-level demand (use power.demand for the BA series), demand before 2019-01-01, the raw un-Adjusted series (this route publishes the Adjusted series only), plant, generator, county, or state attribution, installed capacity (use power.capacity), monthly plant generation (use power.generation), retail sales, revenue, or customers (use power.retail_sales), wholesale prices, or long-horizon forecasts (the forecast is day-ahead only).

Query verified U.S. hourly electricity demand (MW) by balancing authority from EIA-930. Use this for "how much load" questions at the hourly balancing-authority grain: filter or group by `balancing_authority_code`, `region`, `data_date` (or the `data_date_from`/`data_date_to` range), `hour_number`, `datetime_utc`, or `is_imputed`. Pass filters inside the `params` object. Returns JSON aggregates with citations and optional row-level records when `include_records` is true. `demand_mw` is EIA's own cleaned (Adjusted) series, with receipts: the as-reported `demand_mw_raw` and the `is_imputed` flag ride every detail record. `demand_forecast_mw` is the same row's day-ahead forecast, so forecast-vs-actual misses need no second query. History runs hourly from 2015-07-01 onward and is served by default: a bare `data_date` anywhere in that window answers from the newest promoted vintage covering it, and the response `as_of` is that knowledge cut. A query with NO calendar window (no `data_date`, `data_date_from`, or `data_date_to`) and no calendar-axis `group_by` defaults to the latest day that has reported demand — not the full history — and says so in a `default_latest_day` note; group by `data_date` or `datetime_utc`, or pass a date range, to read a series over time. Pin `as_of` to an earlier vintage to reproduce exactly what was served then; one response may cite several source files, and every citation carries its own file and vintage. An empty result names the served coverage window in an `empty_scope` note. Demand is NOT additive across balancing authorities: a result summing more than one BA carries a `ba_aggregation` scope note and ranking remainders omit the demand metrics — group by `balancing_authority_code` for the source-grain series. Does not determine plant, generator, county, or state attribution (EIA-930 carries no such IDs, and BA footprints do not follow state lines), US48 or regional totals (computed rollups are refused; EIA's own published series is the named follow-up), installed capacity (MW — use power.capacity), monthly plant generation (use power.generation), retail sales/revenue/customers (use power.retail_sales), wholesale prices, or long-horizon forecasts (the EIA-930 forecast is day-ahead only).

Query verified raw EIA-923 fuel receipts and delivered fuel costs. Returns one Page 5 Fuel Receipts and Costs row per published receipt: plant/month, fuel, supplier, purchase type, source physical quantity, and delivered cost in EIA's stated cents/MMBtu. Filter by plant, month/range, exact source strings, state, fuel, cost status, or source-reported balancing authority code; `{"state":"TX","balancing_authority_code":"ERCO"}` returns an ERCOT slice in one call. Quantity units remain fuel-specific (short tons, barrels, or Mcf). EIA withholds costs for some plants. The raw `.` marker is preserved in `fuel_cost_raw`, the numeric cost is null, and `fuel_cost_status` explicitly reports `withheld` for unregulated receipts. Missing is never zero or imputed. This tool does not derive heat rates, efficiency, marginal cost, generation cost, or $/MWh; combine the cited raw atoms outside exascale.build if analysis requires those judgments. Every quantity or cost can be verified against its exact workbook cell.

Query verified U.S. monthly net electricity generation (MWh) from EIA-923. Use this for "how much was generated" questions by state, source-reported balancing authority code, fuel, prime mover, sector, plant, or generator, for a given month. For a fuel total or a fuel mix (e.g. "coal generation", "top fuels"), filter or group by `fuel_group` — it sums the several energy_source_code values a fuel spans (coal alone is 6 codes), so a total is correct-by-construction; use the raw `energy_source_code` only when you want one exact as-reported code, since it splits coal/biomass across sub-codes. Select one `atom`: `by_fuel` (default — the complete plant total) or `by_generator` (generator-level, joinable to EIA-860M); never sum across atoms. History runs monthly from 2014-01 onward and is served by default: a bare `data_month` anywhere in that window answers from the newest promoted vintage covering it, and the response `as_of` is that knowledge cut (pin `as_of` to any date to reproduce what was served then — it resolves to the newest vintage at or before it; an empty result names the served window in an `empty_scope` note). `balancing_authority_code` is reported by EIA only from 2018 onward — a BA-filtered query cannot see earlier months. Pass filters inside the `params` object. Returns JSON aggregates with citations down to the exact source month-cell. Does not determine installed capacity (MW — use power.capacity), demand/load, wholesale prices, fuel cost, heat rate, capacity factor, or real-time/hourly dispatch.

Query the CAISO generator interconnection queue — California ISO's public Public Queue Report, the waiting line of projects that have REQUESTED to connect to the CAISO grid (California, plus the out-of-state edges it studies: NV, AZ). Returns cited, project-level records with CAISO's full published structure: the net megawatts to grid (`net_mw_to_grid`, CAISO's own headline figure) and the per-component Type/Fuel/MW triplets for hybrids (`type_1..3`, `fuel_1..3`, `mw_1..3`, plus an `is_hybrid` flag), the as-reported `application_status`, the cluster `study_process` (C01..C14, plus serial/legacy tracks), the three-valued deliverability status (`deliverability_status` = Full Capacity / Partial Capacity / Energy Only) with `tpd_allocation_percentage` / `tpd_allocation_group` / `offpeak_deliverability`, location (`state`, `county`, derived `county_fips`, `utility`, `pto_study_region`), the per-phase study statuses, and lifecycle dates (`ir_receive_date`, `queue_date`, `proposed_online_date`, `current_online_date`, and — for completed projects — `actual_online_date`). Group or filter by `application_status`, `state`, `county_fips`, `deliverability_status`, `study_process`, `fuel_1`, `type_1`, `utility`, `pto_study_region`, `offpeak_deliverability`, `tpd_allocation_group`, `suspension_status`, `ia_status`, or (group only) `is_hybrid`; filter `queue_date` by the `queue_date_from` / `queue_date_to` range. Pass each parameter as a top-level key of `params` (flat — not nested). Example: `{"application_status": "ACTIVE", "fuel_1": "Battery", "state": "CA"}` for active battery requests in California; `{"group_by": ["application_status"]}` for net MW and project counts by status; `{"application_status": "ACTIVE", "group_by": ["deliverability_status"]}` for the active pipeline split by deliverability. Returns JSON aggregates with citations and optional row-level records when `include_records` is true; every value carries `source`, `as_of`, and a `source_row` verifiable with get_source_evidence_v1. `net_mw_to_grid` is REQUESTED capacity, not built: historically the large majority of queued megawatts withdraw before they are built, so the report is withdrawn-dominated. NEVER read a queue-MW total as installed or operating capacity — it is additive across distinct projects but is a REQUESTED total only. Scope by `application_status`: `ACTIVE` is the live pipeline, `COMPLETED` is built and in service (and carries an `actual_online_date`), `WITHDRAWN` left the queue. CAISO publishes no separate built-MW column — `net_mw_to_grid` is served under CAISO's own name and never relabeled or duplicated as a built figure. For built/operating capacity use query_power_capacity_v1. CAISO only — never summed, deduped, or compared across ISOs. For the MISO interconnection queue use query_power_interconnection_queue_v1; for PJM use query_power_interconnection_queue_pjm_v1 (or query_power_interconnection_queue_pjm_cycle_v1 for PJM's cluster/cycle grid); for the NYISO (New York) queue use query_power_interconnection_queue_nyiso_v1; for the ISO-NE (New England) queue use query_power_interconnection_queue_isone_v1; for the ERCOT (Texas) queue use query_power_interconnection_queue_ercot_v1; for the SPP (central US) queue use query_power_interconnection_queue_spp_v1. This tool serves CAISO's Public Queue Report (Cluster 14 and prior, plus the serial/legacy tracks); CAISO's separate current-cluster intake file is a distinct publication and is not served here. CAISO reports no data-center / load type, and this tool does not infer one — that interpretation is the analyst's, from cited rows.

Query the ERCOT generator interconnection queue — ERCOT's public GIS Report (EMIL PG7-200-ER), the waiting line of generation projects that have REQUESTED to connect to the ERCOT (Texas) grid. Returns cited, project-level records with ERCOT's full published structure across four lifecycle sheets (Large Gen + Small Gen = active; Inactive Projects; Cancellation Update): the requested `capacity_mw` (ERCOT publishes ONE capacity figure — no summer/winter split), the ERCOT `fuel` and `technology` codes (e.g. SOL/PV solar, OTH/BA battery, GAS/CC combined-cycle, WIN/WT wind — HYD is HYDROGEN, hydro is WAT), the `cdr_reporting_zone` (NORTH/SOUTH/WEST/COASTAL/HOUSTON/PANHANDLE), the `interconnecting_entity`, the `poi_location`, the composite `gim_study_phase` token string, and the milestone dates (`screening_study_started`, `fis_approved`, `ia_signed`, `construction_start`/`construction_end`, `approved_for_energization`/`approved_for_synchronization`, `projected_cod`). Group or filter by `application_status`, `size_category`, `fuel`, `technology`, `cdr_reporting_zone`, `county_fips`, `state`, `gim_study_phase`, or `interconnecting_entity`; filter `projected_cod` by the `projected_cod_from` / `projected_cod_to` range. Pass each parameter as a top-level key of `params` (flat — not nested). Example: `{"application_status": "ACTIVE", "fuel": "SOL"}` for active solar requests; `{"application_status": "ACTIVE", "group_by": ["fuel"], "order_by": "capacity_mw", "top_n": 5}` for the active pipeline's biggest fuels by requested MW. The GIS Report is published MONTHLY and its full history is queryable — this is NOT a single point-in-time snapshot. Omit `as_of` for the latest month, or pass `as_of` (a date) to get the queue as it stood at a past month: `as_of` resolves to the newest monthly snapshot at or before it, with vintages back to 2018-12 (the floor; an earlier `as_of` is refused, naming the floor). Example: `{"application_status": "ACTIVE", "as_of": "2019-06-30"}` returns the active queue as of mid-2019. Each month is a full point-in-time snapshot (a project that has since withdrawn is simply absent from later months — query the earlier `as_of` to see it), so a multi-month trend is one query per month; `as_of` is the history axis, not a row filter. Returns JSON aggregates with citations and optional row-level records when `include_records` is true; every value carries `source`, `as_of`, and a `source_row` verifiable with get_source_evidence_v1. `capacity_mw` is REQUESTED capacity, not built: historically the large majority of queued megawatts withdraw before they are built. NEVER read a queue-MW total as installed or operating capacity — it is additive across distinct rows but is a REQUESTED total only. ERCOT prints NO status column, so `application_status` is derived from the sheet ERCOT files the project on: `ACTIVE` is the live pipeline (Large/Small Gen), `INACTIVE` and `CANCELLED` are projects that recently left the queue (the Inactive / Cancellation sheets list RECENT departures, NOT the full historical withdrawn set). The build-progress reading is carried SEPARATELY in `gim_study_phase` (e.g. "SS Completed, FIS Completed, IA") + the milestone dates and is never collapsed into `application_status`. For built/operating capacity use query_power_capacity_v1. ERCOT only — never summed, deduped, or compared across ISOs. For the MISO interconnection queue use query_power_interconnection_queue_v1; for PJM use query_power_interconnection_queue_pjm_v1 (or query_power_interconnection_queue_pjm_cycle_v1 for PJM's cluster/cycle grid); for the CAISO (California) queue use query_power_interconnection_queue_caiso_v1; for the NYISO (New York) queue use query_power_interconnection_queue_nyiso_v1; for the ISO-NE (New England) queue use query_power_interconnection_queue_isone_v1; for the SPP (central US) queue use query_power_interconnection_queue_spp_v1. This tool serves ERCOT's GIS Report, which is GENERATION-only; ERCOT's separate large-load / data-center interconnection queue is an unstructured source (TAC-meeting PDF slides) and is NOT served here, and this tool does not infer which projects are data-center-driven — that interpretation is the analyst's, from cited rows.

Query the ISO-NE generator interconnection queue — ISO New England's public IRTT "public queue" report, the waiting line of projects that have REQUESTED to connect to the New England grid (CT, MA, ME, NH, RI, VT). Returns cited, project-level records with ISO-NE's full published structure (all 31 columns of the rendered report): the three megawatt readings kept SEPARATE (`net_mw`, `summer_mw` = max summer output, `winter_mw` = max winter output — `net_mw` is 0 for the many Capacity-Network-Resource-only requests, a real value, not missing), the request `request_type` (G = Generation / ETU = Elective Transmission Upgrade / TS = Transmission Service), the space-delimited multi-value `fuel_type` (EIA energy-source codes, e.g. "SUN BAT"), the `unit_type` and service code `serv` (CNR = Capacity Network Resource / NR = Network Resource), the `jurisdiction` (F = FERC / N = Non-FERC), the ISO-NE load `zone`, the per-stage study statuses (`fs_status` … `ia_status`) with their study-document links, location (`state`, `county`, derived `county_fips`, `poi`), and lifecycle dates. Group or filter by `application_status`, `project_status`, `request_type`, `unit_type`, `fuel_type`, `serv`, `jurisdiction`, `zone`, `state`, `county_fips`, or `cluster`; filter `requested_date` by the `requested_date_from` / `requested_date_to` range. Pass each parameter as a top-level key of `params` (flat — not nested). Example: `{"application_status": "A", "request_type": "G", "state": "MA"}` for active generation requests in Massachusetts; `{"group_by": ["application_status"]}` for requested MW and project counts by status. Returns JSON aggregates with citations and optional row-level records when `include_records` is true; every value carries `source`, `as_of`, and a `source_row` verifiable with get_source_evidence_v1. `net_mw` / `summer_mw` / `winter_mw` are REQUESTED capacity, not built: historically the large majority of queued megawatts withdraw before they are built, so the queue is withdrawn-dominated. NEVER read a queue-MW total as installed or operating capacity — it is additive across distinct rows but is a REQUESTED total only. ISO-NE publishes net, summer-peak and winter-peak MW separately — served under ISO-NE's own labels and never blended into one nameplate. Scope by `application_status`: `A` = Active (the live pipeline), `C` = Commercial (built and in service — the built reading), `W` = Withdrawn. ISO-NE ALSO carries a separate build-progress `project_status` (Under Study / Under Construction / In Service / …) — kept distinct from `application_status`, never collapsed. For built/operating capacity use query_power_capacity_v1. ISO-NE only — never summed, deduped, or compared across ISOs. For the MISO interconnection queue use query_power_interconnection_queue_v1; for PJM use query_power_interconnection_queue_pjm_v1 (or query_power_interconnection_queue_pjm_cycle_v1 for PJM's cluster/cycle grid); for the CAISO (California) queue use query_power_interconnection_queue_caiso_v1; for the NYISO (New York, incl. load interconnection requests) queue use query_power_interconnection_queue_nyiso_v1; for the ERCOT (Texas) queue use query_power_interconnection_queue_ercot_v1; for the SPP (central US) queue use query_power_interconnection_queue_spp_v1. ISO-NE publishes no data-center / load request type (all rows are generation or transmission), and this tool does not infer one — that interpretation is the analyst's, from cited rows.

Query the NYISO generator + load interconnection queue — New York ISO's public waiting line of projects that have REQUESTED to connect to the New York grid. Uniquely among ISOs, NYISO publishes a Load Projects tab — load interconnection requests (large-load demand), served as-reported — and since its 2026-07 edition tags each load request with its own `End-Use` class (`end_use`, e.g. DAT / DAT-AI / DAT-CM, served verbatim). Returns cited, project-level records with NYISO's full published structure across every lifecycle tab (nine tabs through 2026-06; seven since NYISO's 2026-07 restructure): summer and winter peak megawatts kept SEPARATE (`sp_mw` = SP, the max summer output; `wp_mw` = WP, the max winter output), the Load Projects tab's `peak_mw_load` with NYISO's own `end_use` class and `sis_bundle` study-batch code (both 2026-07 onward, null before), the as-reported study-phase code (`study_status_code` — NYISO's numeric key, labeled `S` through 2026-06 and `Project Status #` / `NYISO Status` since), the request `record_type` and `project_type`, the `type_fuel` codebook, the energy-storage capability, the NYISO load `zone` (A–K), location (`state`, `county`, derived `county_fips`, `point_of_interconnection`, `utility`), and lifecycle dates (`ir_date`, `last_update`, the milestone dates, and the Year/Qualifier `proposed_cod` kept verbatim). Group or filter by `application_status`, `sheet_name`, `state`, `county_fips`, `study_status_code`, `record_type`, `type_fuel`, `zone`, `utility`, `studies_available`, or `end_use`; filter `ir_date` by the `ir_date_from` / `ir_date_to` range. Pass each parameter as a top-level key of `params` (flat — not nested). Example: `{"application_status": "ACTIVE", "type_fuel": "S"}` for active solar requests; `{"sheet_name": "Load Projects"}` for the load interconnection requests; `{"end_use": "DAT-AI", "application_status": "ACTIVE"}` for the load requests NYISO itself codes DAT-AI; `{"group_by": ["application_status"]}` for requested MW and project counts by lifecycle. Returns JSON aggregates with citations and optional row-level records when `include_records` is true; every value carries `source`, `as_of`, and a `source_row` verifiable with get_source_evidence_v1. `sp_mw` / `wp_mw` / `peak_mw_load` are REQUESTED capacity, not built: historically the large majority of queued megawatts withdraw before they are built, so the queue is withdrawn-dominated. NEVER read a queue-MW total as installed or operating capacity — it is additive across distinct project-rows but is a REQUESTED total only. NYISO publishes summer (SP) and winter (WP) peak MW separately — they are served under NYISO's own names and never blended into one nameplate. Scope by `application_status` (ACTIVE / WITHDRAWN / IN_SERVICE / AFFECTED_SYSTEM / AFFECTED_SYSTEM_WITHDRAWN — the lifecycle tab's reading, overridden to the withdrawn form when a row carries NYISO's own status code 0, per the workbook's printed '0=Withdrawn' key) or by `sheet_name`; the `In Service` tab is the built reading. A project may appear on more than one tab (the grain is sheet + queue_position), so the counts are project-rows, not deduped projects. For built/operating capacity use query_power_capacity_v1. NYISO only — never summed, deduped, or compared across ISOs. For the MISO interconnection queue use query_power_interconnection_queue_v1; for PJM use query_power_interconnection_queue_pjm_v1 (or query_power_interconnection_queue_pjm_cycle_v1 for PJM's cluster/cycle grid); for the CAISO (California) queue use query_power_interconnection_queue_caiso_v1; for the ISO-NE (New England) queue use query_power_interconnection_queue_isone_v1; for the ERCOT (Texas) queue use query_power_interconnection_queue_ercot_v1; for the SPP (central US) queue use query_power_interconnection_queue_spp_v1. NYISO's Load Projects tab is served as-reported: `end_use` is NYISO's OWN classification (NYISO publishes no key for the codes), and this tool does NOT infer an end use NYISO did not print — interpretation beyond the code is the analyst's, from cited rows.

Query PJM's cluster/cycle service-request grid — the cluster view of PJM's interconnection process: the TC1/TC2 transition cycles (re-processing the pre-Order-2023 serial backlog) and the reopened steady-state cycles (C01+, the new intake). A SEPARATE PJM publication from the full New Services queue (query_power_interconnection_queue_pjm_v1) — richer per-project cluster detail; the two share rows and are never combined. Returns cited, project-level records with PJM's full cluster schema: the cluster `cycle` (TC1 / TC2 / C01 …) and `stage` (phase / decision point), the `developer`, requested megawatts (`requested_max_output_mw` = MFO, `requested_summer_mw`, `requested_winter_mw`), the realized built `in_service_mw`, long-term-firm transmission `ltf_mw`, location (`state`, `county`, derived `county_fips`), `fuel` and `project_type` as PJM reports them, the single `status`, and the phased System-Impact-Study report URLs + statuses. Group or filter by `cycle`, `stage`, `status`, `state`, `county_fips`, `project_type`, `capacity_or_energy`, `fuel`, `developer`, `transmission_owner`, or (group only) `is_hybrid`; filter `submitted_date` by range. Pass each parameter as a top-level key of `params` (flat). Example: `{"cycle": "C01", "status": "Active"}` for the live reopened-cycle pipeline; `{"group_by": ["cycle"]}` for counts by cluster cycle. Returns JSON aggregates with citations and optional row-level records when `include_records` is true; every value carries `source`, `as_of`, and a `source_row` verifiable with get_source_evidence_v1. The `requested_*` figures are REQUESTED capacity, not built: historically the large majority of queued megawatts withdraw before they are built. NEVER read a requested-MW total as installed/operating capacity — additive across distinct projects but a REQUESTED total only. PJM also reports `in_service_mw` (the realized built MW). For built/operating capacity use query_power_capacity_v1. PJM cluster grid only. This and PJM's New Services queue (query_power_interconnection_queue_pjm_v1) are different publications that share rows — never summed or compared across them; never across ISOs (the MISO queue is query_power_interconnection_queue_v1; the CAISO queue is query_power_interconnection_queue_caiso_v1; the NYISO queue is query_power_interconnection_queue_nyiso_v1; the ISO-NE queue is query_power_interconnection_queue_isone_v1; the ERCOT queue is query_power_interconnection_queue_ercot_v1; the SPP queue is query_power_interconnection_queue_spp_v1). PJM reports no data-center / load type, and this tool does not infer one.

Query the PJM New Services (interconnection) queue — the public waiting line of projects that have REQUESTED to connect to the PJM grid (the mid-Atlantic RTO incl. Northern Virginia, PA, NJ, MD, OH, VA, WV and more). Returns cited, project-level records with PJM's full published structure: requested megawatts (`requested_max_output_mw` = MFO, `requested_summer_mw` = MW Capacity / summer net, `requested_winter_mw` = MW Energy / winter net), the realized built `in_service_mw` for completed projects, location (`state`, `county`, derived `county_fips`), `fuel` and `project_type` as PJM reports them, the single as-reported `status`, the study-document URLs and per-stage statuses, and lifecycle dates. Group or filter by `state`, `county_fips`, `status`, `project_type`, `capacity_or_energy`, `fuel`, `project_ac_dc`, `transmission_owner`, the study statuses, or (group only) `is_hybrid`; filter `submitted_date` by the `submitted_date_from` / `submitted_date_to` range. Pass each parameter as a top-level key of `params` (flat — not nested). Example: `{"state": "VA", "project_type": "Generation Interconnection", "status": "Active"}` for active generation requests in Virginia; `{"group_by": ["status"]}` for requested MW and project counts by status. Returns JSON aggregates with citations and optional row-level records when `include_records` is true; every value carries `source`, `as_of`, and a `source_row` verifiable with get_source_evidence_v1. The `requested_*` figures are REQUESTED capacity, not built: historically the large majority of queued megawatts withdraw before they are built. NEVER read a requested-MW total as installed or operating capacity — it is additive across distinct projects but is a REQUESTED total only. Filter `status` (Active / Withdrawn / In Service / Under Construction / …) to scope the queue; the full export is withdrawn-dominated. PJM also reports `in_service_mw` — the realized BUILT MW for in-service projects (a separate, built figure). For built/operating capacity use query_power_capacity_v1. PJM only — never summed, deduped, or compared across ISOs. For the MISO interconnection queue use query_power_interconnection_queue_v1; for the CAISO (California) queue use query_power_interconnection_queue_caiso_v1; for the NYISO (New York, incl. load interconnection requests) queue use query_power_interconnection_queue_nyiso_v1; for the ISO-NE (New England) queue use query_power_interconnection_queue_isone_v1; for the ERCOT (Texas) queue use query_power_interconnection_queue_ercot_v1; for the SPP (central US) queue use query_power_interconnection_queue_spp_v1. For PJM's NEW cluster/cycle process — the TC1/TC2 transition cycles and the reopened steady-state Cycle 1 (C01+), with cycle/stage/developer detail — use query_power_interconnection_queue_pjm_cycle_v1 (a separate PJM publication; never combined with this one). PJM reports no data-center / load type, and this tool does not infer one — that interpretation is the analyst's, from cited rows.

Query the SPP generator interconnection queue — Southwest Power Pool's public GI Summary report, the waiting line of generation projects that have REQUESTED to connect to the SPP grid (the ~14-state central-US RTO: OK, KS, TX panhandle, NE, NM, MO, CO, ND, SD, AR, LA and more). Returns cited, project-level records with SPP's full published structure: the requested `capacity_mw` (SPP's headline `Capacity` figure) PLUS five other labeled MW columns SPP publishes — `max_summer_mw`, `max_winter_mw`, `requested_max_injection_mw`, `requested_nrd_mw`, `nameplate_capacity_mw` — served separately and NEVER blended; the `generation_type` (Wind / Solar / Battery/Storage / Thermal / Hybrid / Hydro — SPP encodes hybrids natively as `Hybrid`, so no is-hybrid is invented) and free-text `fuel_type` (slash-delimited combos like `Solar/Storage` kept whole); the study `current_cluster` (e.g. `DISIS-2024-001`, `Surplus`, `RTOE Transitional Cluster`) and regional `cluster_group` (`01 NORTH` … `05 SOUTHWEST`); the transmission owner `to_at_poi`; the `service_type` (`ER/NR`, `ER`, `NR`); the `substation_or_line`; and the lifecycle dates (`request_received`, `in_service_date`, `commercial_operation_date`, `date_withdrawn`). Group or filter by `native_status`, `generation_type`, `fuel_type`, `service_type`, `current_cluster`, `cluster_group`, `to_at_poi`, `county_fips`, or `state`; filter `request_received` / `commercial_operation_date` by their `_from` / `_to` ranges. Pass each parameter as a top-level key of `params` (flat — not nested). Example: `{"native_status": "DISIS STAGE", "generation_type": "Solar"}` for solar in the DISIS study stage; `{"native_status": "DISIS STAGE", "group_by": ["state"], "order_by": "capacity_mw", "top_n": 5}` for the active study pipeline's biggest states by requested MW. Returns JSON aggregates with citations and optional row-level records when `include_records` is true; every value carries `source`, `as_of`, and a `source_row` verifiable with get_source_evidence_v1. `capacity_mw` is REQUESTED capacity, not built: historically the large majority of queued megawatts withdraw before they are built — in the SPP file ~66% of rows are `WITHDRAWN`. NEVER read a queue-MW total as installed or operating capacity — it is additive across distinct rows but is a REQUESTED total only. Always scope by `native_status`, which is SPP's OWN status vocabulary served VERBATIM (`IA FULLY EXECUTED/ON SCHEDULE`, `IA FULLY EXECUTED/COMMERCIAL OPERATION`, `IA FULLY EXECUTED/ON SUSPENSION`, `IA PENDING`, `DISIS STAGE`, `FACILITY STUDY STAGE`, `SPECIAL STUDY`, `ERAS`, `TERMINATED`, `WITHDRAWN`, …); it is never mapped to a lifecycle enum and there is no derived active/withdrawn flag — that equivalence is the analyst's. For built/operating capacity use query_power_capacity_v1. SPP's GI Summary is regenerated on demand and SPP keeps no per-vintage archive, so this serves SPP's CURRENT queue (the response `as_of` is SPP's own "Last Updated On" stamp); it is NOT a deep point-in-time history — history accrues forward from first capture, so there is no `as_of` time-travel parameter. SPP only — never summed, deduped, or compared across ISOs. For the MISO interconnection queue use query_power_interconnection_queue_v1; for PJM use query_power_interconnection_queue_pjm_v1 (or query_power_interconnection_queue_pjm_cycle_v1 for PJM's cluster/cycle grid); for the CAISO (California) queue use query_power_interconnection_queue_caiso_v1; for the NYISO (New York) queue use query_power_interconnection_queue_nyiso_v1; for the ISO-NE (New England) queue use query_power_interconnection_queue_isone_v1; for the ERCOT (Texas) queue use query_power_interconnection_queue_ercot_v1. SPP's GI queue is GENERATION-only and infers no load/data-center type — that interpretation is the analyst's, from cited rows.

Query the MISO generator interconnection queue — the public waiting line of projects that have REQUESTED to connect to the MISO grid (the 15-state Midwest/South footprint). Returns cited, project-level records: requested megawatts (net summer / net winter), location (`state`, `county`, derived `county_fips`), fuel and technology as MISO reports them, three independent status dimensions (`application_status`, `study_phase`, `post_gia_status`), and queue / withdrawn / in-service dates. Group or filter by `state`, `county_fips`, `application_status`, `study_phase`, `post_gia_status`, `fuel_type`, `facility_type`, `service_type`, `study_group`, `study_cycle`, or `is_hybrid`; filter `queue_date` by the `queue_date_from` / `queue_date_to` range. Pass each parameter as a top-level key of `params` (flat — not nested). Example: `{"state": "IN", "fuel_type": "Solar", "application_status": "Active"}` for active solar requests in Indiana; `{"group_by": ["application_status"]}` for requested MW and project counts by status. Returns JSON aggregates with citations and optional row-level records when `include_records` is true; every value carries `source`, `as_of`, and a `source_row` verifiable with get_source_evidence_v1. This is REQUESTED capacity, not built: historically the large majority of queued megawatts withdraw before they are built. NEVER read a requested-MW total as installed or operating capacity — it is additive across distinct projects but is a REQUESTED total only. Filter `application_status` (Active / Withdrawn / Done) to scope the queue; the full export is withdrawn-dominated. For built/operating capacity use query_power_capacity_v1. MISO only — never summed, deduped, or compared across ISOs into a national total (each ISO's methodology, inclusion rules, and withdrawal rates differ). For the PJM interconnection queue (the mid-Atlantic RTO incl. Northern Virginia) use query_power_interconnection_queue_pjm_v1 (or query_power_interconnection_queue_pjm_cycle_v1 for PJM's new cluster/cycle process incl. the reopened Cycle 1); for the CAISO (California) queue use query_power_interconnection_queue_caiso_v1; for the NYISO (New York, incl. load interconnection requests) queue use query_power_interconnection_queue_nyiso_v1; for the ISO-NE (New England) queue use query_power_interconnection_queue_isone_v1; for the ERCOT (Texas) queue use query_power_interconnection_queue_ercot_v1; for the SPP (central US) queue use query_power_interconnection_queue_spp_v1 — separate ISO blocks, never combined with this one. MISO reports no data-center / load type, and this tool does not infer one — that interpretation is the analyst's, from cited rows.

Query accepted native-XBRL FERC Form 1 large-steam plant facts. Returns one separately cited XBRL fact per respondent, report year, raw plant name, and source concept: installed capacity, net generation, plant-cost balance items, fuel expense, and individual operation and maintenance lines. Values and units are as filed; nominal dollars are not adjusted, allocated, divided by generation, or combined into a derived O&M total. Plant names remain raw strings with no EIA ID matching. Every value verifies against its exact archive member, XBRL fact ID, context, concept, and SHA-256. Coverage is the Form 1 filing population, not the full fleet. ERCOT-only merchant entities largely do not file, so ERCOT coverage is partial and plant absence means not present in served filings—not zero. `ercot_relevance=true` is a one-call filter based only on the respondent's raw states-served disclosure mentioning Texas; it is not a plant-location claim. v0 covers accepted native XBRL (report year 2021 onward) and the large-steam schedule including nuclear; hydro, pumped storage, migrated historical XBRL, and Visual FoxPro-era filings are explicitly outside v0.

Query verified ERCOT wholesale electricity prices — ERCOT's Day-Ahead Market Settlement Point Prices ($/MWh, EMIL NP4-190-CD), the price cleared the day before each operating day at every ERCOT (Texas) settlement point, served hourly. Returns cited prices for each (`settlement_point`, `delivery_date`, `hour_ending`): the per-hour `price_usd_per_mwh` in detail records, plus `avg_price_usd_per_mwh`, `min_price_usd_per_mwh`, and `max_price_usd_per_mwh` over the result scope. Each `settlement_point` is one of ERCOT's locations — a trading Hub (e.g. `HB_NORTH`, `HB_HOUSTON` — the regional benchmark prices), a Load Zone (e.g. `LZ_HOUSTON`), a Resource Node (one generator's connection point), or a DC-tie — and `settlement_point_type` carries ERCOT's OWN verbatim classification code (`HU`/`LZ`/`RN`/`LZ_DC` and finer codes) so an agent can tell a regional benchmark from a single-plant node. Filter or group by `settlement_point`, `settlement_point_type`, `hour_ending`, or `delivery_date`; filter a date window with `delivery_date_from` / `delivery_date_to`, or one day with `delivery_date`. Pass each parameter as a top-level key of `params` (flat — not nested). Example: `{"settlement_point": "HB_NORTH", "delivery_date": "2026-06-20", "group_by": ["hour_ending"]}` for the North hub's 24 hourly day-ahead prices; `{"delivery_date": "2026-06-20", "group_by": ["settlement_point_type"]}` for the average price by location type. With no date filter the result defaults to the latest delivery day with prices (it does not scan all history); served delivery coverage begins 2014-05-02 from ERCOT's official Data Access Portal archive. Historical settlement-point names remain exactly as published, and names absent from the current pinned type list have a null type rather than being rewritten. Returns JSON with citations and optional row-level records when `include_records` is true; every value carries `source`, `as_of` (the delivery day), and a `source_row` verifiable with get_source_evidence_v1. A price is INTENSIVE ($/MWh): it is AVERAGED, min'd, and max'd over a scope — NEVER summed (a "total price" is meaningless, so no sum is offered). An average across more than one settlement point (e.g. a hub and a resource node together) is indicative, not a settlement value — group_by `settlement_point` for the per-point series, or filter to one point/type. This is the DAY-AHEAD hourly market, NOT real-time / 5-minute prices. ERCOT's day-ahead settlement-point price is a TOTAL only — there is no energy/congestion/loss component split and no loss component, and none is synthesized. ERCOT's own hour-ending label (`01:00`..`24:00`) and `dst_flag` are carried verbatim (a day is 24 hours normally, 25 on the fall-back DST date with `02:00` repeated, 23 on spring-forward). A settlement point is an electrical/aggregate location, not a plant — ERCOT supplies no county or lat/lon, so the only geography anchor is `state` = TX. This is a PRICE ($/MWh) — not capacity (MW) or generation (MWh): for installed/operating capacity use query_power_capacity_v1, for electricity generated use query_power_generation_v1. ERCOT only — prices are NEVER blended, averaged, or compared across ISOs (each ISO's market design and redistribution license differ); this tool serves ERCOT's day-ahead settlement-point prices alone.

Query verified U.S. annual retail electricity sales — billed MWh, revenue, and customer counts — by utility, state, and customer sector from EIA-861. Use this for "who sold how much power to whom" questions at the annual utility×state×sector grain: filter or group by `data_year`, `state`, `sector` (residential / commercial / industrial / transportation), `part`, `service_type`, `ownership`, `ba_code`, `data_type`, `eia_utility_id`, or `utility_name`. Pass filters inside the `params` object. Returns JSON aggregates with citations down to the exact stacked sector/measure cell, and optional row-level records when `include_records` is true. Defaults keep totals faithful: the in-row `total` sector block is excluded unless named explicitly (it duplicates the four sectors); EIA's state-level Adjustment (99999) and Withheld (88888) sentinel rows stay in state totals but are auto-excluded from any utility-keyed query; territories are excluded unless `included_in_default_us_metrics` is false. A result mixing service types carries a `service_type_mix` note quoting the file's own law — revenue sums Parts A,B,C,D but sales/customers sum A,B,D only (Part C delivery re-counts Part B energy). History spans data years 2016–2024, one annual census per year, each its own vintage. Reach an earlier year through `as_of`, not `data_year`: `as_of` resolves to the newest census at or before it (so `as_of` 2018-06-01 — or just 2018 — returns the 2018 census) and the response echoes that resolved `as_of`. `data_year` only filters within the resolved vintage, so `data_year` 2018 under the default `as_of` (latest = 2024) returns an empty scope, not 2018; the default serves 2024, a multi-year trend is one query per year, and an `as_of` before 2016 is refused, naming the floor. Does not determine hourly or peak load (sales are billed MWh over a year — use power.demand), facility-level or data-center-specific load, county-level detail, average retail price (cents/kWh — deferred), the ~1,700 small short-form (EIA-861S) utilities, or monthly freshness (this is the annual census, not the monthly EIA-861M sample).

Query verified U.S. private construction spending ($ millions) for data centers and semiconductor/computer-electronics manufacturing plants, from the U.S. Census Bureau's Value of Construction Put in Place (C30). Use this for "how much is being spent BUILDING data centers (or chip fabs) in the US" questions — the construction buildout in dollars, not capacity or investment. Filter by `category` ("data_center" — Census's named subcategory under Office; or "computer_electronic_electrical" — the semiconductor/computer-electronics manufacturing line under Manufacturing), `basis` ("seasonally_adjusted" = a seasonally-adjusted ANNUAL RATE, or "not_seasonally_adjusted" = the NOT-adjusted MONTHLY LEVEL), `data_month` (one month, ISO first-of-month e.g. "2026-04-01") or the `data_month_from`/`data_month_to` range, `year`, and `revision_status` ("preliminary", "revised", or "final"). Group by any of `category`, `basis`, `data_month`, `year`, or `revision_status`. Pass each parameter as a top-level key of `params` (flat — not nested under a `filter`, `filters`, or `where` key). Example: `{"category": "data_center", "basis": "seasonally_adjusted", "data_month": "2026-04-01"}` for one month; add `"group_by": ["data_month"]` over a `data_month_from`/`data_month_to` range for a series. Returns JSON aggregates with citations and optional row-level records when `include_records` is true — every value cites the exact Census workbook, sheet, row, and column. The two categories are DISTINCT series and are never conflated: `data_center` is data-center buildings; `computer_electronic_electrical` is the chip/electronics-manufacturing (fab) line — the CHIPS-Act build-out. `basis` is the other fork: the seasonally-adjusted series is an ANNUAL RATE (what the current monthly pace annualizes to), while the not-seasonally-adjusted series is the actual MONTHLY LEVEL. `revision_status` carries Census's own preliminary/revised/final marking verbatim. Data is monthly; the data-center series begins 2014-01. The response `as_of` is the release vintage (Census revises monthly); pin `as_of` to an earlier vintage to reproduce what was served then. NOT additive: `construction_spending_musd` is a published per-(category, basis, month) reading, so a total that mixes the two bases (an annual rate + a monthly level), or that sums the seasonally-adjusted ANNUAL-RATE series across months, is not a real figure — such a result carries a `construction_aggregation` scope note and ranking remainders omit the metric. Filter to one `basis` and `group_by data_month` for a series over time. Does not determine total data-center INVESTMENT (servers, chips, cooling, equipment — this is construction put-in-place only; Census does not publish an investment total), data-center MW capacity, count, square footage, or location (use the power.* capabilities for capacity and the interconnection queue), which company or project is building (Census C30 has no operator breakdown), public or government construction (this is PRIVATE construction only), or construction outside these two categories.

Query verified U.S. employment, establishments, and wages — total and by industry (data centers, semiconductors, construction, retail, accommodation, food service) — for any county, state, or the nation, from the U.S. Bureau of Labor Statistics' Quarterly Census of Employment and Wages (QCEW). Use this for two families of questions: (1) "how many people work in / how many establishments / what wages in data centers or chip fabs" — INDUSTRY employment, not an "AI jobs" count; and (2) the place-based question — "what happened to a county's employment, wages, construction, or local economy (e.g. during and after a data-center / fab buildout)": total covered employment plus the buildout-phase and induced-sector series for every US county, quarterly since 2014. Filter by `industry_code` — each code lives at ONE aggregation depth, shown here with its agglvl codes (national/state/county): "10" Total, all industries — every covered job (agglvl 10/50/70 = all ownerships combined; 11/51/71 = split by ownership) "23" Construction (sector; 14/54/74) "44-45" Retail trade (sector; 14/54/74) "721" Accommodation (3-digit; 15/55/75) "722" Food services & drinking places (3-digit; 15/55/75) "236220" Commercial & institutional building construction (6-digit; 18/58/78) "518210" Computing infrastructure / data processing / web hosting — the data-center industry (6-digit; 18/58/78) "334413" Semiconductor & related device manufacturing (6-digit; 18/58/78) `agglvl`'s first digit is geography (1 national / 5 state / 7 county); pick ONE industry_code and the matching agglvl for its depth to get a clean additive scope. Also filter by `own_code` ("5" = Private — the usual one; "1"/"2"/"3" = federal/state/local government; "0" = Total Covered, only on industry "10"), geography (`state` USPS e.g. "VA", `county_fips` 5-digit e.g. "51107" Loudoun County, or `area_fips`), and time (`year`, `qtr` "1"-"4", the `quarter` ISO first-of-quarter e.g. "2025-10-01", or a `quarter_from`/`quarter_to` range). Group by any of `industry`, `industry_code`, `ownership`, `own_code`, `state`, `county_fips`, `agglvl`, `year`, `qtr`, or `quarter`. Pass each parameter as a top-level key of `params` (flat — not nested under a `filter`/`where` key). Examples: `{"industry_code": "518210", "own_code": "5", "agglvl": "18", "quarter": "2025-10-01"}` — the national private data-center-industry figure; `{"industry_code": "10", "own_code": "0", "agglvl": "70", "county_fips": "51117", "group_by": ["quarter"], "quarter_from": "2014-01-01"}` — total employment in Mecklenburg County VA, quarterly (the "did the buildout move the county" series); swap `"industry_code": "23", "own_code": "5", "agglvl": "74"` for its construction sector. Returns JSON aggregates with citations and optional row-level records when `include_records` is true — every value cites the exact BLS file, row, and quarter. Measures: `qtrly_estabs` (establishments), `month1_emplvl`/`month2_emplvl`/`month3_emplvl` (employment in each month of the quarter — intra-quarter SNAPSHOTS; average them for a quarterly figure, never sum them), `total_qtrly_wages` ($), and `avg_wkly_wage` ($, on detail records). Industry series are DISTINCT and NESTED: "10" contains the sectors, "23" contains "236220" — never sum across industry codes (each depth has its own agglvl, so a mixed-depth scope draws the `qcew_hierarchy` note). WHERE JOBS ARE COUNTED: at the employer's ESTABLISHMENT, not the work site. A construction crew building in county X for a contractor based in county Y counts in county Y — so a county's construction series understates on-site buildout labor staffed by outside contractors. SUPPRESSION: BLS withholds a confidential (small county × industry) cell by zeroing its employment and wages and marking `disclosure_code` "N" (or "-"). Those are served as NULL (absent), never as zero — the establishment count is still shown. Roughly half of county × data-center cells are withheld ("10" and sector-level cells are rarely withheld); an absent value means "BLS withheld it," not "no jobs." A scope containing withheld cells returns a `qcew_suppression` note counting them: sums skip the NULLs, so summed employment/wages UNDERCOUNT — for a state or national figure use BLS's own row at that level (agglvl 5x/1x) instead of summing finer cells. Data is quarterly back to 2014 Q1, ~6-month lag (latest ≈ 2025 Q4). The response `as_of` is the release vintage; pin `as_of` to reproduce an earlier vintage. NAICS VINTAGE: each year is served exactly as BLS coded it — 2014-2021 under NAICS 2017, 2022Q1-forward under NAICS 2022; BLS never recodes history. The 2022 revision REDEFINED 518210 (retitled to "computing infrastructure providers…"), so a 518210 series crossing 2022Q1 mixes two definitions — a level shift at that boundary (e.g. Loudoun County VA: −45% in one quarter) is establishment reclassification, not jobs lost. Compare 518210 within one vintage side of 2022Q1, or say so when crossing it. NOT additive across hierarchy or time: counts and employment are additive across distinct AREAS within ONE `agglvl` + ONE `own_code` + ONE quarter (e.g. all counties in a state). They are NOT additive across geographic levels (national already contains states/counties — a `qcew_hierarchy` note flags it), across industry depths ("10" contains the sectors and 6-digit codes), across ownership totals ("0"/"8" contain their components), or across QUARTERS (employment is a per-quarter stock — a `qcew_period` note flags it; quarterly wages, by contrast, sum across quarters into an annual bill). Filter or group_by to avoid double-counting. Does not determine "AI jobs" or a data-center-only headcount (NAICS 518210 is the broader computing-infrastructure / hosting industry), jobs at the work SITE (counted at the employer's establishment — see above), a definition-constant 518210 series across 2022Q1 (the NAICS vintage break — see above), industries beyond the eight pinned series (e.g. electrical contractors 238210 — largely absent/suppressed at county grain), employment for a withheld cell (served absent), occupation or job-title detail (QCEW is industry, not occupation), which company employs (no employer breakdown), or MSA / metro figures (national / state / county only).

Query verified U.S. monthly IMPORTS of semiconductor-manufacturing EQUIPMENT (HS-8486) — customs value (USD) by country of origin — from the U.S. Census Bureau's International Trade data. Use this for "is the fab buildout actually tooling up, and who supplies the machines" questions — the equipment leg of the fab lifecycle: construction spending (ai_infrastructure.construction) measures the shell, this measures the tools flowing in, and chip imports (ai_infrastructure.trade) measure the output side. HS-8486 covers machines and apparatus used solely or principally to MANUFACTURE semiconductor boules/wafers, devices, and integrated circuits — AND flat-panel displays (Census does not split them at this level); it is NOT the chips themselves (those are HS-8542). Filter by `country` (the verbatim Census name, e.g. "JAPAN", "NETHERLANDS", "KOREA, SOUTH"), `cty_code` (the Census country code), `country_level` ("total" = the all-countries TOTAL, "country" = an individual country, "grouping" = a Census bloc/continent like ASIA / APEC / EU), `year`, `data_month` (one month, ISO first-of-month e.g. "2026-04-01") or the `data_month_from`/`data_month_to` range. Group by any of `country`, `cty_code`, `country_level`, `data_month`, or `year`. Pass each parameter as a top-level key of `params` (flat — not nested under a `filter`, `filters`, or `where` key). Example: `{"country_level": "country", "group_by": ["country"], "order_by": "general_value_usd", "top_n": 5}` for the top tool-supplying countries; `{"country_level": "total", "group_by": ["data_month"]}` for the national trend. Returns JSON aggregates with citations and optional row-level records when `include_records` is true — every value cites the exact Census response row, re-verifiable via get_source_evidence_v1. Measures: `general_value_usd` (general imports value) and `consumption_value_usd` (imports for consumption) — value only; no tool counts, and no tool-type or vendor breakdown (one HS4 heading: no lithography-vs-deposition-vs-etch split, no per-manufacturer series such as ASML). NEVER SUM across country rows: Census's groupings (ASIA, APEC, EU, OECD, ASEAN, the continents) OVERLAP each other and the individual countries, and the all-countries TOTAL contains everything — so adding rows double-counts; a cross-row sum returns a country_aggregation note and nulls the metric in ranking remainders. Filter `country_level=total` for the U.S. national figure. Country is the country of ORIGIN (Census attribution), not which U.S. fab, state, or operator receives the equipment — there is no U.S. place breakdown. Imports only (not exports), customs value (not landed/CIF/duty), and recent months are preliminary and revised in later Census releases.

Query verified U.S. semiconductor & electronic-component PRODUCTION and CAPACITY UTILIZATION — the Federal Reserve's monthly G.17 industrial-production index (2017=100) and capacity-utilization rate (percent) for NAICS 3344 — from the Board's own release, history to 1972. Use this for "are the domestic fabs actually producing / how hot are they running" questions — the OUTPUT leg of the fab lifecycle: construction spending (ai_infrastructure.construction) measures the shell, equipment imports (ai_infrastructure.equipment_trade) the tools flowing in, chip imports (ai_infrastructure.trade) what crosses the border; this measures domestic production and how much of the installed capacity is in use. NAICS 3344 is "semiconductor and OTHER electronic component" manufacturing — the finest split the Fed publishes here (broader than semiconductors alone, and NOT the same slice as QCEW's 334413). Filter by `series_kind` ("ip" = the production index, on both bases; "capacity_utilization" = percent of capacity in use, seasonally adjusted only; "capacity" = the capacity index behind the rate), `series_name` (the verbatim Fed series, e.g. "IP.G3344.S", "CAPUTL.G3344.S"), `basis` ("seasonally_adjusted" / "not_seasonally_adjusted" — IP only), `year`, `data_month` (ISO first-of-month, e.g. "2026-05-01") or the `data_month_from`/`data_month_to` range. Group by any of `series_name`, `series_kind`, `basis`, `data_month`, or `year`. Pass each parameter as a top-level key of `params` (flat — not nested). Example: `{"series_kind": "capacity_utilization", "group_by": ["data_month"], "data_month_from": "2024-01-01"}` for the utilization trend; `{"series_kind": "ip", "basis": "seasonally_adjusted", "group_by": ["year"]}` for the production index by year (an average per year). Returns JSON aggregates with citations and optional row-level records when `include_records` is true — every value cites the exact Fed SDMX observation, re-verifiable via get_source_evidence_v1. Measures are avg/min/max per reading — `avg_ip_index`, `avg_capacity_utilization_pct`, `avg_capacity_index` (+ min/max variants): an index or a rate is INTENSIVE, so multi-month figures are AVERAGES, never sums (the Fed publishes its own quarterly/annual aggregations, which this block does not serve — monthly grain only). An index is not dollars and not unit counts (2017=100). Capacity and utilization exist seasonally adjusted only — their not-seasonally-adjusted cells are structurally absent, never zero. Averaging the IP index across both bases returns a production_aggregation note — filter or group by basis instead. National industry aggregate: no state, county, fab, or company breakdown. Every monthly release revises history (as_of carries the vintage).

Query verified U.S. monthly IMPORTS of integrated circuits (HS-8542) — customs value (USD) by country of origin — from the U.S. Census Bureau's International Trade data. Use this for "how much $ of chips did the US import (from Taiwan / South Korea / in total) and how is it trending" questions. HS-8542 is ALL integrated circuits (processors, memory, amplifiers, parts) — NOT AI-accelerator / GPU-specific. Filter by `country` (the verbatim Census name, e.g. "TAIWAN", "KOREA, SOUTH"), `cty_code` (the Census country code, e.g. "5830"), `country_level` ("total" = the all-countries TOTAL, "country" = an individual country, "grouping" = a Census bloc/continent like ASIA / APEC / EU), `year`, `data_month` (one month, ISO first-of-month e.g. "2026-04-01") or the `data_month_from`/`data_month_to` range. Group by any of `country`, `cty_code`, `country_level`, `data_month`, or `year`. Pass each parameter as a top-level key of `params` (flat — not nested under a `filter`, `filters`, or `where` key). Example: `{"country_level": "country", "group_by": ["country"], "order_by": "general_value_usd", "top_n": 5}` for the top source countries; `{"country_level": "total", "group_by": ["data_month"]}` for the national trend. Returns JSON aggregates with citations and optional row-level records when `include_records` is true — every value cites the exact Census response row, re-verifiable via get_source_evidence_v1. Measures: `general_value_usd` (general imports value) and `consumption_value_usd` (imports for consumption) — value only; HS-8542 reports no meaningful quantity at this level, so there is no chip count. NEVER SUM across country rows: Census's groupings (ASIA, APEC, EU, OECD, ASEAN, the continents) OVERLAP each other and the individual countries, and the all-countries TOTAL contains everything — so adding rows double-counts. Filter `country_level=total` for the U.S. national figure, `country_level=country` for individual countries, or group_by country for the per-country series; a cross-row sum returns a country_aggregation note and nulls the metric in ranking remainders. Country is the country of ORIGIN (Census attribution), not where a chip is installed — there is no U.S. state/county breakdown. Imports only (not exports), customs value (not landed/CIF/duty), and recent months are preliminary and revised in later releases.

Query the verified share of US manufacturing plants USING industrial robots — plus workers exposed and robotics capex — from the Census Industrial Robotic Equipment product (the first official federal robotics-adoption statistics). Use this for "are factories actually adopting robots" questions — the INSTALLED-BASE reading the import data cannot see. Serves the percent of plants with robots and the percent of employees at plants with robots (both published as FRACTIONS of 1: 0.121 = 12.1%), Census's demeaned variants, and capital expenditures for robotic equipment ($1000) — by manufacturing industry (`naics_code`, 2/3-digit), by `state`, and by `plant_size` band. Filter by `edition` ("asm_2018_2021" = the ASM annual series; "ec_2022" = the 2022 Economic Census), `table` (the workbook sheet — exactly one of: "Percent of... NAICS", "Percent of... Geo", "Percent of... Geo demean", "Robot adopters vs not", "Robot adoption and plant size", "CapEx... NAICS", "CapEx... Geo", "CapEx and plant size"), `data_year` (2018-2022), `naics_code`, `state`, `plant_size`, or `geo_area_name` ("United States" for the national row). Group by any of `edition`, `table`, `naics_code`, `naics_title`, `state`, `plant_size`, `data_year`. Pass each parameter as a top-level key of `params` (flat — not nested under a `filter`, `filters`, or `where` key). Example: `{"table": "Percent of... Geo", "data_year": 2022, "group_by": ["state"], "order_by": "avg_pct_plants_with_robots", "top_n": 10}` for the most-automated states; `{"table": "Percent of... NAICS", "edition": "asm_2018_2021", "naics_code": "336", "group_by": ["data_year"]}` for transportation-equipment adoption over the ASM years. Returns JSON aggregates with citations and optional row-level records when `include_records` is true — every value cites its exact workbook cell-group, re-verifiable via get_source_evidence_v1. THE ENGRAVED BOUNDARY: the two editions are NEVER spliced into one trend — the 2022 Economic Census reaches the small-plant universe the ASM sample does not (US plants-with-robots: 12.1% ASM-2021 vs 6.4% EC-2022 — a COVERAGE change, not a decline; every cross-edition scope carries an edition_scope note). Percents are INTENSIVE shares: avg/min/max over a scope, never summed. Capex sums UNDERSHOOT below the published totals wherever suppression bites (the published "United States" / "31-33" rows are the totals). Suppressed cells (D/S/A, decoded by the file's own footnotes) are null values with their verbatim letter — never zero; (s)-flagged estimates (standard error > 40%) carry their flag. Manufacturing plants only; adoption SHARES and capex, never robot counts (no official count of installed robots exists — the import unit-count series is query_robotics_trade_v1); an EXPERIMENTAL Census product (its own label); no edition after 2022 exists.

Query verified U.S. monthly IMPORTS of INDUSTRIAL ROBOTS — customs value (USD) AND unit counts (number of robots) — by country of origin, from the U.S. Census Bureau's International Trade data. Use this for "how many robots is the US importing, from whom, and what are they worth" questions — the only high-frequency official U.S. robotics series. Covers the nomenclature's two robot-specific HS-10 codes, served as the `commodity` dimension: "8479500000" (INDUSTRIAL ROBOTS, NESOI — multipurpose: welding/assembly arms, AMRs) and "8428700000" (INDUSTRIAL ROBOTS FOR LIFTING, HANDLING, LOADING OR UNLOADING — created by HS 2022; no data before 2022-01, a structural absence, never zero). Filter by `commodity`, `country` (the verbatim Census name, e.g. "JAPAN", "CHINA", "KOREA, SOUTH"), `cty_code` (the Census country code), `country_level` ("total" = the all-countries TOTAL, "country" = an individual country, "grouping" = a Census bloc/continent like ASIA / APEC / EU), `year`, `data_month` (one month, ISO first-of-month e.g. "2026-04-01") or the `data_month_from`/`data_month_to` range. Group by any of `commodity`, `country`, `cty_code`, `country_level`, `data_month`, or `year`. Pass each parameter as a top-level key of `params` (flat — not nested under a `filter`, `filters`, or `where` key). Example: `{"commodity": "8479500000", "country_level": "country", "group_by": ["country"], "order_by": "general_quantity_units", "top_n": 5}` for the top robot-supplying countries by unit count; `{"country_level": "total", "group_by": ["data_month", "commodity"]}` for the national trend per code. Returns JSON aggregates with citations and optional row-level records when `include_records` is true — every value cites the exact Census response row, re-verifiable via get_source_evidence_v1. Measures: `general_value_usd` / `consumption_value_usd` (customs value) and `general_quantity_units` / `consumption_quantity_units` (Census's "NO" unit of measure = the number of robots). NEVER SUM across country rows: Census's groupings (ASIA, APEC, EU, OECD, ASEAN, the continents) OVERLAP each other and the individual countries, and the all-countries TOTAL contains everything — adding rows double-counts; a cross-row sum returns a country_aggregation note and nulls the metrics in ranking remainders; filter `country_level=total` for the U.S. national figure. The two commodity codes ARE disjoint — adding them is legitimate — but a combined time series changes composition at 2022-01 (a commodity_scope note flags it). This is the import FLOW, not the installed base or operational stock of robots in U.S. factories; no maker, model, or humanoid breakdown (customs-classified); country is the country of ORIGIN, not which U.S. state or factory receives the robots; imports only (not exports); customs value (not landed/CIF/duty); recent months are preliminary and revised in later Census releases.

List available exascale.build data capabilities for agent discovery before querying. Also call this BEFORE stating that a capability is not available — client tool lists are cached and this surface grows; anything listed here is reachable via query_capability_v1 even if your tool list predates it.

Query any served capability by name — the generic twin of the named query tools, reaching every capability including ones newer than your client's cached tool list. Pass `capability` as either a capability id from list_capabilities_v1 (e.g. "power.price_ercot") or a query primitive name (e.g. "query_power_price_ercot_v1"), and `params` as the same flat JSON object the named query tool accepts — call describe_capability_v1 first for valid filters, e.g. {"capability": "power.capacity", "params": {"state": "TX", "group_by": ["energy_source_code"]}}. Returns the identical cited envelope as the named tool: same rows, same citations, same as_of.

Query verified U.S. capacity factor — how hard a fleet actually runs — by joining EIA-860M capacity and EIA-923 generation. Requires `data_month`: one ISO month start, e.g. "2026-01-01". If the user names no month, ask which one (or state the month you chose); if a month is not covered, the error lists the months that are — do not retry blindly. capacity_factor = net generation (MWh) / (operating nameplate capacity (MW) × hours in the month), computed over plant×fuel present in BOTH sources, so scope is auto-aligned. Optional `group_by` of `state` and/or `fuel_group`, and `state`/`fuel_group` filters. Returns the capacity factor per group with its generation and capacity, a `coverage` declaration (what share of in-scope capacity/generation matched), and a citation to BOTH the capacity and the generation source row. Basis is nameplate; storage is excluded; the capacity snapshot is matched to the month. Does not determine per-generator capacity factor, a net-summer/winter basis, or months absent from either source.

Query verified EIA natural-gas price records from two public series. `atom="henry_hub_daily_spot"` returns one trading-day Henry Hub spot price in EIA's published $/MMBtu unit (series RNGWHHD). `atom="state_electric_power_monthly"` returns one state-month average price paid by electric-power consumers in EIA's published $/Mcf unit; `{"atom":"state_electric_power_monthly","state":"TX"}` is the Texas power-sector proxy slice in one call. Filter either atom by `date`, `date_from`/`date_to`, series, state, or price status. The state series is an aggregate of what the state's power sector paid that month, not a plant-level fact. EIA null values remain explicit `price=null` records with `price_status="source_missing"`—never zero or imputed. The two source units are never converted or blended; mixed-unit avg/min/max are null. This tool does not assign proxies to plants or derive heat rates, $/MWh, spark spreads, or any ratio. API revisions are preserved as immutable capture vintages selected by `as_of`. Every price cites its exact archived response record, series id, period, value cell, and SHA-256 for source-evidence verification.

Fetch and hash-verify the raw source row behind a returned citation. Pass a citation object inside `params`. Two ready-to-pass shapes come straight from the query tools: each aggregate row's `citations[ref].verify` object, or a detail record's `citation` (from include_records). Either proves the number with no re-query. The tool verifies the raw workbook SHA-256 before returning source-header row values. Use this when an agent must prove an answer from the underlying source row.

Query the verified FCC satellite licensing docket — every space-station (SAT) filing in the FCC's own daily IBFS database dump, back to the 1960s — by applicant, application type, status, and filing date. Use this for "who is authorized to operate what in orbit, what has been filed, and where does each filing stand" questions — the satellite-buildout licensing pipeline. Each filing carries the FCC's public filing key (`file_number`, e.g. "SATLOA2025061800149"), the `callsign` (e.g. "S3069" = SpaceX Gen2), the application type and status in the FCC's OWN vocabulary — verbatim codes plus the FCC's own decode text from the same dump vintage (`app_type_code` "LOA" = Launch and Operating Authority, "STA" = Special Temporary Authority, "MOD" = Modification; `status_code` "A/C" = Action Complete, "ATPN" = Action Taken Public Notice — codebooks in describe) — the full lifecycle date family (filed / granted / expires / …), the FCC's plain-English `description` of the filing, and the applicant identity (`applicant_name`, the FCC's verbatim registrant, e.g. "Space Exploration Holdings, LLC"). Filter by `applicant_name`, `app_type_code`, `status_code`, `callsign`, `file_number`, `state` (the APPLICANT's address state), `applicant_country`, `report_period` (the filing date) via `report_period_from`/`report_period_to`, or `date_grant`/`date_expire` ranges. Group by any of `applicant_name`, `app_type_code`, `status_code`, `state`, `applicant_country`. Pass each parameter as a top-level key of `params` (flat — not nested under a `filter`, `filters`, or `where` key). Example: `{"applicant_name": "Space Exploration Holdings, LLC", "group_by": ["app_type_code"]}` for one operator's filing mix; `{"report_period_from": "2020-01-01", "group_by": ["applicant_name"], "order_by": "source_record_count", "top_n": 10}` for the most active filers of the 2020s. Returns JSON aggregates with citations and optional row-level records when `include_records` is true — every record cites its exact row in the FCC's dump, re-verifiable via get_source_evidence_v1. THE ENGRAVED BOUNDARY: new-filing intake into IBFS structurally ENDED at the FCC's ICFS system cutover (~mid-2025), and ICFS publishes no bulk data — so filings SUBMITTED after the cutover are not in this docket, and counts near/after 2025 UNDERCOUNT new filing activity (say so when answering; every response carries an icfs_cutover note). Status and lifecycle updates on the filings that ARE here continue to flow daily. A filing is an authorization EVENT: never a satellite count (one NGSO grant can cover thousands of satellites), never an orbital catalog (satellites in orbit are not served here), never launch activity (FAA data, not served here). `state`/`applicant_city` are the APPLICANT's mailing address — satellites are not in states. Earth stations (SES) and non-satellite FCC dockets are out of scope. The one measure is `source_record_count` (filings in scope).