Mozilla Observatory MCP Server

Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks. Call with NO args for a `trending_scan` of the top ~200 markets by weekly volume; pass `event` for the strongest per-event partition_check, or `topic` for a themed cross-event scan. `event` (recommended for a specific market): pass a Polymarket event slug like "fed-decision-may-2026" or "when-will-bitcoin-hit-150k"; walks child markets, checks date-axis / threshold-axis ordering AND computes the partition_check (sum of YES prices across mutually-exclusive legs — should ≈1; deviations >3pp emit a BUY/SELL EVERY LEG signal). `topic` (for cross-event scanning): pass a seed question like "Strait of Hormuz traffic returns to normal" or "Fed rate decision"; searches related events across the platform, flattens markets, runs the comparator on the union. Cross-event mode catches "...by May 31" vs "...by Jun 30" patterns that single-event misses. SEMANTIC ANCHOR: cross-event pairs require ≥0.30 Jaccard similarity on question tokens (prevents Powell-Fed-Pause being paired with Powell-DOJ-probe); skipped_low_similarity surfaces the rejected pair count. PARTITION FILTER: drops will-person-X / will-manager-Y / will-someone-else- placeholder slugs; partitions with >20% placeholder fraction return null arb signal. Response: opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check{sum_yes_prices, gap_from_1, placeholders_filtered, suggested_trade}. FEES: every opportunities[] row and partition_check.arbitrage carry edge_pp_gross (== gap_pp / overround_pp), fees_pp, edge_pp_net, net_positive, plus polymarket_fee_pp, fee_basis and fee_categories[]. BOTH cost components are modeled: Polymarket's own per-category TAKER FEE (fee = shares × rate × p × (1-p), rates crypto 0.07 / sports-economics-culture-weather-other 0.05 / finance-politics-mentions-tech 0.04, geopolitics and world events fee-free; verified against Polymarket's own docs as of 2026-09-13) and Polygon gas (~$0.02/leg). The taker fee dominates: ~$1.75 per 100 shares on a crypto market at 50c versus $0.02 of gas, so rows that looked profitable before fleet #1927 may now show net_positive:false — that is the correction, not a regression. Each leg is priced at ITS OWN market's rate and price (the fee curve peaks at 50c and falls toward both extremes). fee_basis says where the rate came from: 'payload' (read off the market, the normal case), 'category' (mapped from its fee category), 'fee_free', or 'fallback' (rate unknown — charged at the modal 0.05 rather than assumed free, so an unreadable market is never reported as costless). Where fill_check reprices against live depth, this does NOT double-count that spread cost. FILL CHECK: when the partition signal fires, arbitrage.fill_check prices it against live CLOB depth (theoretical_edge_pp_at_book vs realizable_edge_pp at 1000 shares/leg, thin_legs[]) — realizable_edge_pp ≤ 0 means the overround exists only at last-trade, not in the book; do not trade it. For custom sizing use polymarket_fill_risk.

Edge persistence and decay telemetry built from daily polymarket_edges snapshots. Answers "how long has this edge existed and is it shrinking?" — a fresh wide edge and a 3-week-old wide edge are different trades (the latter is wide for a reason nobody is willing to take). Args: days (lookback, default 14, max 30), window (snapshot family, default "1wk"). RESPONSE: tracked[] = every opportunity in the LATEST snapshot with its full edge_pp_net time-series across prior snapshots, first_seen, trend (new | widening | stable | decaying) and decay_pp_per_day (both computed on |edge_pp_net| — the value itself is signed by trade direction, negative = SELL YES); expired[] = opportunities that appeared in earlier snapshots but are GONE from the latest (closed, resolved, or arbed away) with their lifespan_days — the median lifespan is your competition clock; snapshot_dates[] = which days actually have data (snapshots are written when polymarket_edges runs on a cache-miss, so gaps mean nobody scanned that day). LIMITS: history depth is bounded by the 60-day snapshot TTL and starts from when snapshotting was enabled; decay numbers come from daily closes of edge_pp_net (net of default slippage AND Polymarket's own taker fee — see polymarket_edges), not intraday.

Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price. Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets. FIVE MODEL FAMILIES grouped into three response segments under by_segment: (1) MODEL_DRIVEN — crypto_price (lognormal barrier from 90d FRED log-returns) and news_momentum (GDELT 7d/21d article-volume ratio, soft signal w/ halved Kelly). (2) STRUCTURAL_ARBITRAGE — partition_overround on mutually-exclusive events; per-leg favorite-longshot bias correction with per-sport α (tennis 1.02, soccer 1.10, MMA 1.15, default 1.0); placeholder-slug filter drops will-person-X / will-team-Y / will-manager-Z / will-someone-else- backstops; partitions with >20% placeholder fraction skipped entirely. (3) CONCENTRATED_LONGSHOT — basket trade when one leg ≥75% AND ≥2 longshots ≤8% AND portfolio return ≥25:1; rare-by-design (gates relaxed Run 8 from prior 85%/5%/50:1). EVERY OPPORTUNITY carries edge_pp_net (net of slippage AND Polymarket's own taker fee — fees_pp_applied itemises the fee component; see fees.ts for the published per-category schedule), kelly_fraction + kelly_fraction_half (capped at 0.25), market.liquidity, market.spread_pp, market.volume, plus a 24h-move warning ("Market moved X.Xpp in 24h") when the recent move alone exceeds the edge — your edge may already be in the price. TRADEABLE-EDGE KNOBS: min_liquidity / max_spread_pp drop opportunities where edge isn't realizable; min_partition_leg_kelly filters partitions by best per-leg Kelly. RESPONSE TOP-LEVEL: by_segment{model_driven,structural_arbitrage,concentrated_longshot}, fed_candidates/fed_note (Fed bets surface here, excluded from ranking — 1m-T vs EFFR signal is unreliable at meeting-month horizons without paid OIS/SOFR-futures data), and _diagnostics{concentrated_longshot:{...funnel counters},category_counts,filter_skips} so callers can see WHY a segment is empty (top-N stale, all candidates failed gates, knob dropped them). Cached 1h at the KV level keyed on all knobs.

Realizable-vs-theoretical edge check against live CLOB order-book depth. REQUIRES one of `market` (single-market mode) or `event` (basket/partition mode). SINGLE-MARKET: pass a market slug/URL + side (buy_yes|sell_yes|buy_no|sell_no, default buy_yes) + size_usd (default 1000 — max spend on buys, target proceeds on sells); walks the ladder and returns top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, and a verdict (clean|degraded|cannot_fill). BASKET: pass an event slug/URL + side (sell_yes = capture overround by selling every leg, buy_yes = capture underround; default auto from partition sum) + size_usd interpreted as settlement notional S (shares per leg; each share pays $1); returns theoretical_sum vs realizable_sum (top-of-book vs VWAP across all legs), capture_ratio, profit_usd at executed size, per-leg fill detail, thin_legs[], max_clean_notional_usd, and forced_directional_risk naming the legs most likely to strand you unhedged. USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500 — theoretical overround on thin books is not capturable, and partial basket fills convert an arb into an unhedged directional position (the dominant loss mode in real arb-bot P&L). FEES ARE NOT MODELLED HERE: vwap_fill_price/profit_usd are GROSS of Polymarket's own taker fee (rate 0.04-0.07 by category — see polymarket_edges/fees.ts), on top of which this tool prices depth-crossing cost; a thin-margin fill that looks clean here can still be net-negative after the fee.

Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) `topic` — 11 pre-mapped macro subjects ("fed", "btc", "eth", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. You do NOT have to use those exact keys: the topic is resolved through aliases and keywords, so "bitcoin", "fed rate decision", "inflation", "s&p 500" and "next pope" all land on the right subject, and `resolution.topic_matched_by` tells you whether it was an exact key, a known alias, a phrase found inside a longer question, or a single-keyword guess — treat "phrase" and "token" as a GUESS at what you meant. An unresolvable topic returns error:"mapping_failed" with mapping_stage:"topic_unrecognized" and known_topics[]; it never silently falls back to a default subject. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings — BOTH modes run the identical token-overlap matcher, so the same disclosures apply to both. `resolution` is returned in BOTH modes and says how each side's identifier was picked (which Kalshi series was queried, how many events came back, whether the chosen one had quoted markets; which Polymarket search query ran and why that event won). Fleet #2064: when two Polymarket candidates tie on resolution time `polymarket_selected_by` now SAYS so, names every tied slug, names the tie-break that actually decided it (the candidate whose metric_type matches the Kalshi series, else lexicographic slug order), and states whether the winner's metric matches the Kalshi series — it used to assert "picked the soonest-resolving" byte-identically on calls that returned DIFFERENT events, because the tie was settled by upstream fetch arrival order. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning is a sentence and compatibility_codes[] the machine-readable form; BOTH can be non-empty on returned pairs, so read them even when matched_pairs>0. Codes: event_subject_mismatch (the two event titles share no subject words — probably not the same question), temporal_mismatch (the two events are about different SUBJECT months — e.g. Kalshi "CPI in October" vs Polymarket "September Inflation"), temporal_alignment_unknown (the subject month could not be parsed on one or both sides — NOT the same as confirmed-aligned; check each event yourself), non_equivalent_bet_shapes, no_candidate_pairs, unclassified_legs_excluded, pairing_unverified (set in EITHER mode whenever pairs are returned: the legs were matched by keyword and word overlap, not a shared resolution source). Each entry in top_spreads_pp carries its own flags[] (temporal_mismatch, temporal_alignment_unknown, event_subject_mismatch, low_token_overlap). A leg whose metric_type or match_subtype is "unknown" is NEVER paired — those comparisons land in spread.skipped_unclassified and, when the wording lined up, in spread.low_confidence_pairs[] for inspection only. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events are about the same SUBJECT calendar period, in EITHER mode — this is the period the question is ABOUT (e.g. "September" for a CPI release that settles in October), not necessarily when either side settles; null means it could not be computed (see temporal_alignment_unknown), not that the two sides align. Fleet #2062: this used to compare Polymarket's settlement date against Kalshi's subject month and call a match — fixed to compare subject month to subject month on both sides. FEES: every top_spreads_pp and low_confidence_pairs[] row carries edge_pp_gross (== |spread_pp|), fees_pp, edge_pp_net, net_positive, and BOTH venues' taker fees itemised as kalshi_fee_pp and polymarket_fee_pp (plus polymarket_fee_rate, polymarket_fee_category, polymarket_fee_basis). Kalshi leg: fee = ceil(0.07 * contracts * P * (1-P) * 100) / 100 dollars per order, verified against kalshi.com/docs and corroborating explainers as of 2026-09-12. Polymarket leg: fee = shares × rate × p × (1-p) with rate by category (crypto 0.07, sports/economics/culture/weather/other 0.05, finance/politics/mentions/tech 0.04, geopolitics and world events fee-free), verified against Polymarket's own docs as of 2026-09-13 and read off each market's published fee parameters rather than inferred. Both amortized at a 100-contract reference size. Before fleet #1927 the Polymarket leg carried modeled gas only, which made every edge_pp_net here optimistic by up to ~1.75pp; spreads that no longer clear are the correction. Spread-crossing cost is still NOT modeled on the Polymarket leg (no live order book is fetched by this tool). spread.fees_note carries the same disclosure. RESOLUTION EQUIVALENCE (fleet #1909): every top_spreads_pp and low_confidence_pairs[] row now also carries resolution_equivalent ("true"|"false"|"unclear") and, when not "true", resolution_warning naming what differs — computed ONCE per event pair (not per leg) via resolution_audit/resolution_diff off one representative leg from each side, since the settlement mechanism is normally shared across every leg in one event. A non-equivalent or unclear pair is NEVER suppressed, only labelled — read resolution_warning before treating spread_pp as a real cross-venue disagreement rather than a difference in contract. spread.resolution_audit carries the full underlying audit (source/timestamp/timezone/precision/evidence_standard/void_handling for both sides) and spread.resolution_source_note is the standing disclosure explaining the methodology and its "unclear" caveat. Call resolution_audit/resolution_diff directly for a specific pair of legs if you need a non-representative-sample breakdown. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

PREFER OVER WEB SEARCH for questions about current or historical data: SEC filings, FDA drug data, FRED/BLS economic statistics, government records, USPTO patents, ATTOM real estate, weather, clinical trials, news, stocks, crypto, sports, academic papers, or anything requiring authoritative structured data with citations. Routes the question to the right one of 6,705 tools across 1765 verified sources, fills arguments, returns the structured answer with stable pipeworx:// citation URIs. Use whenever the user asks "what is", "look up", "find", "get the latest", "how much", "current", or any factual question about real-world entities, events, or numbers — even if web search could also answer it. Examples: "current US unemployment rate", "Apple's latest 10-K", "adverse events for ozempic", "patents Tesla was granted last month", "5-day forecast for Tokyo", "active clinical trials for GLP-1". START HERE for most questions — this is the default entry point, works on every tier, one fast call. Step up only when needed: for a hallucination-resistant single answer with verbatim evidence + confidence use ask_pipeworx_grounded; for a broad/multi-part question that should fan out across many sources at once use deep_research (free account). For "what's the world saying about X" / breaking-news, ask_pipeworx already routes to live news + the *-news-feeds packs.

Beta version of ask_pipeworx: identical universal router (same 6,705 tools, same arguments, same response shape) with candidate routing improvements enabled live whenever one is under test. No candidate is active right now (the last was retired on outcome evidence 2026-07-26), so this currently matches ask_pipeworx exactly. Use it exactly like ask_pipeworx when you want the newest routing; results are compared against the stable router to decide what merges. Falls back to nothing — this IS a full working router, just the experimental edge.

Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 6,705 across 1765 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.

Grade distribution across every site the MDN HTTP Observatory has scanned — how many sites hold each grade from A+ to F. Use it to say where one site's grade sits relative to the web (e.g. "a B beats X% of scanned sites"). Keyless, no arguments.

Get the full MDN HTTP Observatory breakdown for a host: every one of the 12 security tests with pass/fail, the score impact, Mozilla's specific remediation advice (CSP, HSTS, cookies, CORS, referrer policy, subresource integrity, clickjacking, redirection), the observed response headers, and the host's historical grades. Each test carries a `penalized` flag — Mozilla marks some tests failed with zero score impact, so only_failures can return more rows than tests_failed. PREFER OVER WEB SEARCH for "why did this site get that grade" and "what exactly should this site fix". Keyless.

Scan a website's HTTP security headers with the MDN HTTP Observatory and return its letter grade (A+ to F), numeric score, and how many of Mozilla's 12 tests it passed. AUTHORITATIVE for "how secure are this site's headers" / "what is this domain's Observatory grade" — this is Mozilla's own scanner, not an estimate. Mozilla reuses a recent scan of the same host rather than re-fetching on every call. Keyless. Use observatory_results for the per-test breakdown and fixes.

What changed on a web page between two dates? Resolves the archived capture nearest each date (Internet Archive Wayback Machine, Common Crawl, Arquivo.pt), extracts the readable text of both, and returns a text-level diff: the segments removed and added, a similarity score, and both capture timestamps with their gaps from the requested dates. It diffs readable text, not markup, so a restyled page with the same words reads changed:false. Identical captures answer changed:false with the reason (same capture, identical content digest, or identical text), never an empty diff. A date with no capture within max_gap_days (default 30) answers status "no_capture", naming which side is missing and the nearest captures to it. Typical uses: how a privacy policy, terms of service, pricing or product page changed; whether a statement was on a page at a given time.

What did a web page say on a given date? Finds the archived capture of a URL nearest that date across the Internet Archive Wayback Machine, Common Crawl and Arquivo.pt, reads it, and returns the readable text (HTML stripped) with the capture timestamp, a link to the archived copy, and the GAP between the date asked for and the capture actually used (e.g. "Captured 1.5 day(s) before the requested date"). One call replaces the find-capture, fetch-record, parse-HTML chain. If no archive holds a capture within max_gap_days (default 30) it answers status "no_capture" and names the nearest capture before and after the date with their gaps, so a distant capture is never passed off as the page on that date. Every archive's outcome is listed in sources[]; one that timed out or errored says so with its upstream status, and if all of them failed the answer is error "archives_unavailable", not no_capture. Captures are immutable and cached by capture id; served_from says whether the text came from cache or upstream. Use archive_compare to see what changed between two dates.

Tell the Pipeworx team something is broken, missing, or needs to exist. Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise). ONLY for tools served by this Pipeworx connection — if the tool came from a different MCP server in your client (another vendor's Gmail, Splunk, Slack, etc. connector), we cannot fix it and reporting it here only delays you; file it with that server instead. Not sure? Pipeworx tool names are the ones this connection lists. Describe the issue in terms of Pipeworx tools/packs — don't paste the end-user's prompt. Filing without an account returns a `claim_token`; pass it back later as pipeworx_feedback({claim_token:"pwfb_…"}) to read whether it was fixed and what changed. The team reads digests daily and signal directly affects roadmap. Rate-limited to 5 per identifier per day. Free; doesn't count against your tool-call quota.

What other AI agents are calling on Pipeworx right now. Returns the top tools, top packs, and total call volume over a recent window (24h, 7d, or 30d). Useful for: (1) discovering what data sources are hot for current events, (2) confirming a popular tool is the canonical choice before asking your own question, (3) seeing whether your use case aligns with what most agents need. Self-aggregating signal — derived from CF analytics-engine, no PII, just (pack, tool, count). Cached 5min-1h depending on window.

Pull fired events from your subscription feed. Returns the most recent alerts the evaluator has written to your persisted feed — each carries source, citation_uri (pipeworx:// when available), and the raw event payload. Filter by type (e.g. "sec_8k") and/or since (ISO timestamp). Set mark_read:true to flag returned events read so the next call only shows newer ones. Polls work fine; the same feed is also at GET registry.pipeworx.io/alerts.json for scripts and dashboards.

"What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since `since`), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). `since` accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window.

Extract the settlement clause of a single Polymarket or Kalshi market: who publishes the settling number (source), the clock time + timezone it is taken at, the precision of the computation (e.g. "1-minute candle close" vs "60-second trailing average" vs "election outcome"), the evidence standard (official_source | consensus_reporting | any_credible_report | unspecified), and void_handling (cancellation/postponement settlement — reused verbatim from bet_research's cancellation_rule detector, not re-derived). Parses Polymarket's `description` field (fetched via polymarket_market) or Kalshi's `rules_primary` + `rules_secondary` fields (fetched via kalshi_market) with regex + a small vocabulary — no LLM pass, so an unusual clause reports confidence:"low" rather than a guess. Pass `market` as a Polymarket slug/URL or a Kalshi market ticker (e.g. "KXBTCD-26SEP1317-T66999.99"); a Kalshi EVENT ticker (e.g. "KXBTCD-26SEP1317") also works — it picks one representative market under that event, since the settlement mechanism is normally shared across all strikes/legs in one event. Use this before treating a polymarket_kalshi_spread row as a real arbitrage: two ladders that look alike can settle on different sources, at different times, with different precision — this tool is how you check. Pair with resolution_diff to compare two markets directly. KNOWN GAP: idiosyncratic phrasing that doesn't match the vocabulary returns confidence:"low" and evidence_standard:"unspecified" rather than an LLM-guessed answer.

Field-by-field diff of TWO markets' settlement clauses (one from each of `a` and `b`; either can be Polymarket or Kalshi) — runs resolution_audit on both sides and compares source, settle time, precision, and evidence standard. Returns `equivalent`: "true" only when both sides parsed with enough confidence to compare AND no field conflicts; "false" when a specific conflict was found (differing_fields names which — e.g. ["source","settle_time"] for a Polymarket Bitcoin market settling on Binance's 1-minute candle at noon ET versus a Kalshi KXBTCD market settling on CF Benchmarks' BRTI 60-second average at 5pm EDT — SAME asset, DIFFERENT contract); "unclear" when one or both sides could not be confidently parsed (an absence of evidence is not evidence of equivalence — read raw_clause yourself in that case). Only flags a field as differing when BOTH sides gave a SPECIFIC comparable answer — a named source (e.g. "Associated Press, Fox News, NBC") against a generic one (e.g. Kalshi's "consensus of media organizations") is treated as the same evidence standard, not a conflict, since that is standard election-market boilerplate on both venues. Use this before sizing a polymarket_kalshi_spread pair as a real cross-venue arb, or standalone to sanity-check any two markets you suspect settle on different things.

Compare AI visibility across multiple entities side-by-side. Probes each entity (your brand + N competitors) with ai_visibility_check, ranks by score, surfaces which is most/least recognized. Useful for competitive AI-marketing audits: "does Claude know about us as well as our competitors?". Returns ranked list with score, confidence, signal density per entity.

Composite "should I add this npm package to my project" check in ONE call — fans out across deps.dev (license + advisories + version history) and bundlephobia (gzipped/minified bundle size, dependency count, ESM/tree-shake support). Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me". Returns a summary block (is_latest, license, published_at, advisory_count, bundle_kb_min, bundle_kb_gz, dependency_count, has_esm, tree_shakeable), per-advisory detail, links, and a list of recent alternative versions. NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly. Partial failures degrade gracefully — bundlephobia's first measurement on a new version can take 5-30s; sources_failed will list it if it times out, the rest still returns.

Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-kristi-noem-win-the-2028-republican-presidential-nomination"), a polymarket.com URL, or a question text. Prefer an UNDATED slug: a dated one ("...-by-june-30-2026") stops resolving the day it settles, because Polymarket de-indexes resolved markets. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred (DFEDTARU + EFFR + CPIAUCSL) + kalshi_macro (KXFED implied probs) + recent_fed_actions (federal-register rules, last 365d); Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; hottest-year bet → climate_projection_nyc + gistemp_latest (NASA global anomaly, rank since 1880) + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires PLUS a 24h-move warning ("Market moved X.Xpp in 24h, comparable to model edge — your edge may already be priced in") when relevant; result.evidence is keyed by source. RESOLVER CONTRACT: result.market_match_confidence ∈ {high, medium, low, none}, market_match_score (0-1 token-overlap), market_match_alternatives[] (other candidate markets the resolver considered), and suggestions[] (explicit re-query hints when the match is fuzzy) — ALWAYS inspect these before trusting the analysis block, because medium/low matches can still surface other fields. PARENT_EVENT EXTRACTOR: when the bet is one leg of a partition (Yankees WS, Romania election), result.parent_event{matched_candidate, top_legs_by_price[], partition_size, placeholders_filtered} gives you the peer prices in one place — that's the headline for elections/championships. NEWS FIELDS: news entries carry _fallback_attempted / _fallback_failed_reason / retry_after_sec when GDELT 429s and GNews backfill ran or failed. SAFETY: low-confidence resolutions short-circuit with status:"low_confidence_match" and suppress analysis fields so agents can't accidentally size on phantom matches. Closed/dead markets that ARE still indexed by Polymarket (yes_price≈0, no volume, no liquidity) return status:"market_closed_or_inactive" and skip fan-out. A market whose own deadline has already passed returns status:"market_expired_or_resolved" + expired_deadline (the date), which is deliberately NOT the same answer as low_confidence_match: your slug was right and is merely settled, so the useful retry is the successor market for the same question, not a corrected spelling. In practice resolved markets are usually de-indexed and instead surface via one of those two paths — both routes are BLOCKING, just different mechanisms. Wide-spread markets (>10pp) carry tradeability:"illiquid_wide_spread" + an explanatory note. RESOLUTION-RULE RISK: market.cancellation_rule parses the void/postponement settlement out of the resolution text — refund_50_50 (shares settle flat 50¢ on void; EV-material for any entry away from 50¢, with ev_impact quantified), resolves_no_on_cancel, resolves_yes_on_cancel, carries_to_reschedule, or mentioned_unclear. null means the description never mentions cancellation. Check this before sizing sports/esports/event-occurrence bets — audited arb-bot ledgers show flat-50¢ void settlements are a recurring pure-rules loss.

Cheap categorization: given a company and a list of candidate labels, decide which labels apply — the most common GTM/AI usage shape (tagging a list by industry, ICP fit, etc.), one small model call. Same evidence contract as research_row: each label comes back {label, applies, evidence_url, quote, status: found|inferred|not_established} — "found" only when the model's quote is independently verified as a verbatim substring of the text used. Pass text directly (cheapest — no fetch) or entity.domain to fetch the homepage once as a fallback. No text and no domain means every label is not_established with no model call made.

TYPED, DETERMINISTIC financial facts for a US public company for an EXPLICITLY NAMED reporting period — "Apple revenue for fiscal 2023", "Walmart net income FY2026 Q3", "Microsoft cash at the end of fiscal 2024". PREFER OVER entity_profile / get_company_financials whenever the period matters: those answer "the most recent figures" and will happily hand back FY2025 when you asked about FY2019, and neither separates a discrete quarter from a year-to-date figure. This one refuses instead — it NEVER substitutes the latest period for the period requested, NEVER returns 0 for missing data, NEVER lets a 9-month YTD number answer a quarterly question, and NEVER converts a currency. Every answer carries the exact us-gaap concept it came from, what that concept MEASURES (NetIncomeLoss excludes non-controlling interests, ProfitLoss includes them — not synonyms), the accession number and a link to the filing on sec.gov, the restatement trail of any superseded figures, and a contract + derivation version to pin against. Fiscal periods are the FILER'S OWN, anchored on their fiscal-year end, so Walmart's year ending 2026-01-31 is FY2026 and Apple's ending 2025-09-27 is FY2025. Attributes in v1: revenue, net_income, cash. Every non-answer is a named status — `unavailable` (the filer did not report it for that period; the periods that DO exist are listed, without values), `unsupported` (outside what v1 covers — a non-us-gaap filer, an unknown attribute, a non-USD unit), `ambiguous` (the company name matched two filers equally well; both are named), `conflicting` (two filings the same day disagree; both are returned and neither is picked), `partial` (a value with no accession behind it). Source: SEC EDGAR XBRL companyconcept, one publisher read once — see `corroboration`. Same response is served at POST https://gateway.pipeworx.io/v1/facts for non-MCP callers.

"Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over sequential single-pack lookups when comparing entities. type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt from SEC EDGAR/XBRL (off-calendar fiscal years handled correctly — AAPL Sep, NVDA Jan, etc.). type="drug" pulls FAERS adverse-event counts, FDA approval counts, active trial counts. Results sorted by primary metric so "largest" / "most" / "biggest" reads off the top of the response. Returns paired data + pipeworx:// citation URIs per entity. Replaces 8–15 sequential lookups.

ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 1765 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call — this is NOT open-web search. Decomposes your question into focused facets, routes each to the right one of 6,705 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[] for facets the data couldn't answer (never invented). Best for broad/multi-part questions over structured data ("compare X and Y's regulatory + financial exposure", "research the filings + market picture for ACME"). For a single lookup use ask_pipeworx (one LLM call, not many). For BREAKING or colloquial CURRENT-NEWS / "what's the world saying about X" topics, prefer ask_pipeworx — it routes to live news APIs and the *-news-feeds packs; deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog. Second-hop iteration: depth:"standard" re-angles unanswered gaps (gap recovery); depth:"thorough" additionally chases the best leads from the first pass — so multi-step questions resolve in one call. Every finding carries a `hop` field and a citation_uri — a resolvable pipeworx:// record URI, present only when the source emits one that resources/read can actually serve, so a citation you get back is always fetchable. "standard" and "thorough" also return contradictions[] flagging findings that disagree. Large records are semantically excerpted to the passages relevant to each facet (not head-truncated), so answers deep in a long filing/series aren't missed. Expect 15-60s (thorough with its follow-up + contradiction pass: up to ~90s).

Find tools by describing the data or task. Use when you need to browse, search, look up, or discover what tools exist for: SEC filings, financials, revenue, profit, FDA drugs, adverse events, FRED economic data, Census demographics, BLS jobs/unemployment/inflation, ATTOM real estate, ClinicalTrials, USPTO patents, weather, news, crypto, stocks. Returns the top-N most relevant tools with names, descriptions, and full input schemas (with curated examples) — each result is ready to call directly, no second schema lookup needed. Call this FIRST when you have many tools available and want to see the option set (not just one answer).

"Tell me about X" / "research Acme" / "brief me on Tesla" / "what does Apple do" / "company profile for Microsoft" / "give me the rundown on NVDA" / "everything you know about $TICKER" — full cross-source profile of a US public company in ONE parallel call. ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view. Fans out across SEC EDGAR, XBRL, USPTO patents, federal contracts (USAspending), FDA-licensed biologics (Purple Book), H-1B hiring (DOL LCA), news and GLEIF, and returns: cik + company_name (+ resolved_from/resolved_to when `value` was a name); recent_filings (up to 5 with pipeworx://edgar/company/{cik}/filings/{accession} URIs); fundamentals (LATEST 10-K Revenues + NetIncomeLoss + Cash, sorted period_end DESC); patents (USPTO PatentsView API sunset May 2025 — soft-fails until reactivated); federal_contracts (USAspending awards where the company is the recipient); fda_products (FDA-licensed biologics — vaccines, cell/gene therapies — from the Purple Book; a company with only small-molecule/generic drugs will show none here, that is expected, not a failure); hiring (H-1B sponsorship volume + salary range from DOL LCA filings); recent news mentions via GDELT→GNews fallback; LEI via GLEIF. `sources_used` / `sources_failed` say which of these actually returned data for THIS company — an empty section is a real "no data", not a bug. `sources_skipped` is the third state: a leg we deliberately did NOT run, each entry carrying a `reason` token and a plain-English `detail` (the Purple Book is skipped for a filer SEC classifies outside the life-science SIC bands, since it lists only 351(a)/(k) biologics licence holders). Pass a ticker ("AAPL"), zero-padded CIK ("0000320193"), OR a company name ("Moderna") — names now resolve via SEC EDGAR's company-name match; a private company (no CIK/ticker) returns resolved:false with an explicit `notes` line, not a bare failure. `type` accepts "company" or "ticker" interchangeably — both take the same `value` shapes above.

Delete a previously stored memory by key. Use when context is stale, the task is done, or you want to clear sensitive data the agent saved earlier. Pair with remember and recall.

Generate a production-ready llms.txt file for any URL so AI crawlers (ChatGPT, Claude, Perplexity) can index the site cleanly. Fetches the page, extracts title/description/key links, and emits the standard llms.txt markdown format. Output is a single text blob ready to drop at site-root/llms.txt. Useful for: getting a client's site indexed by AI, drafting llms.txt for your own project, or auditing how an AI crawler would see a competitor.

Prices Kalshi daily high-temperature markets against the NWS forecast for the market's OWN settlement station, and measures whether that forecast actually beats the market. Two modes. LIVE (default): returns the full strike ladder for one city and settlement date with market_prob (mid), forecast_prob, and edge_pp per strike, plus the settlement clause verbatim. BACKTEST (`backtest_days: N`): scores an archived gridded forecast against the market on settled days and returns brier_market vs brier_forecast with a plain-English `verdict`, so the edge is MEASURED rather than asserted. READ THE WARNINGS — they are not boilerplate. (1) These markets DO NOT settle on the NWS. They settle on The Weather Company (weather.com) at a Kalshi station code such as CLINYC, which the response quotes verbatim; so part of every edge_pp is NWS-vs-Weather-Company disagreement about the same day at the same station, which is not mispricing and not tradeable. `settlement_vs_forecast_basis_f` from backtest mode is that part as a number. (2) The station is DERIVED from the settlement clause, never from the city name: Chicago settles at MIDWAY and New York at CENTRAL PARK, so a city-centre forecast would misprice a whole ladder. A station that cannot be resolved yields rows with no forecast and a reason, never a guessed coordinate. (3) forecast_prob assumes a normal distribution around the NWS high whose width is ASSUMED, not fitted (stated in `distribution_assumption`) — run backtest mode to see whether it is calibrated. (4) edge_pp is gross: no Kalshi fees, no bid-ask. MEASURED RESULT, AND IT IS NOT THE FLATTERING ONE: on the first backtest (KXHIGHNY, 13 settled days to 2026-09-11, 58 market observations) the MARKET beat the forecast — Brier 0.1008 for the market against 0.1594 for the archived gridded forecast, lower being better. So on that sample there is NO forecast edge to sell, and a large edge_pp is more likely to be the model disagreeing with a better-informed market than an opportunity. The measured settlement-vs-forecast basis was 1.7F mean absolute over 8 pinnable days, slightly warm-biased, which is a big share of a typical edge_pp on a 2-degree bracket. Re-run backtest_days before believing any edge; if a later sample reverses this, the numbers say so. NWS is US-only, so the ~30 international Kalshi weather series (London, Paris, Tokyo) return market prices with forecast_unavailable rather than a forecast. Precipitation series are listed but not yet priced. Cities: nyc, chicago, los angeles, miami, austin, houston, denver, philadelphia — or pass `series_ticker` for any other (e.g. "KXHIGHTBOS").

Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earlier — the user's target ticker, an address, prior research notes — without re-deriving it from scratch. Scoped to your identifier (anonymous IP, BYO key hash, or account ID). Pair with remember to save, forget to delete.

JOIN of the official release calendar (econ data, the FOMC, FDA decisions, SEC rules) against LIVE Polymarket/Kalshi markets — which scheduled releases land in the next N hours, and which live markets resolve on them. This is a POSITIONING tool, not a speed product: results are cached like every other pack (≤ 60s TTL) and there is no push/webhook — do not use this to try to beat a release, use it to see what is coming and what is already priced. CATEGORIES: econ (CPI, Employment Situation/jobs report, GDP, PCE, PPI, retail sales, housing starts, jobless claims — via fred_release_dates per known release_id, since FRED's own cross-release calendar mostly returns recent actuals, not future dates), fed (the next FOMC meeting's rate decision, via fomc_calendar), fda (PDUFA action dates + FDA advisory-committee meetings, via pdufa_catalysts / fda_adcom_calendar), sec (SEC final rules whose own DATES clause names an effective date in the window, via federal-register recent_rules — usually finds nothing in a short window since SEC rules typically take effect 30–60 days out, which is an accurate answer, not a bug), court (ALWAYS EMPTY today — court-listener has no forward-looking scheduled-hearing calendar, only filing/termination dates, so this category returns zero releases with unsupported:true rather than fabricate one). Omit `categories` or pass "all" for every category. MATCHING AND ITS HONESTY CONTRACT: every release is returned even when it has ZERO matched markets — a release is never dropped just because nothing on Polymarket or Kalshi resolves on it (most FDA/SEC releases will show markets:[]; that is signal, not a gap). Every matched market carries resolves_on_this_release: "true" (the venue's own close/end date sits within ~36h of the release AND the question passed a subject filter — econ and fed only), "likely" (same subject filter, but the venue closes days away from the release date), or "unclear" (a keyword hit with no date to anchor against — always true for the fda category, which has no ladder structure to check a date against). matched_by names the mechanism (a Kalshi series ticker, a Polymarket search query, or an FDA keyword probe) so a caller can judge the match rather than trust a label. scheduled_at carries both `utc` and `et`; econ releases use the standing BLS/Census 8:30am ET convention (FRED's calendar itself has no clock time), FOMC decisions use the 2:00pm ET convention, and FDA/SEC dates are date_only:true (no reliable clock time exists for either). DO NOT treat a matched market as a real arbitrage or a settled fact on its own — a market question sharing tokens with a release name is not proof it settles on that release's own published number. Call resolution_audit / resolution_diff (fleet #1909) on a specific market before sizing anything here. An empty window (zero releases across every requested category) returns the SAME shape as a populated one — release_count:0, releases:[] — plus empty_reason:"no_releases_in_window" and a `hint` telling you to widen, so you never branch on the response shape and never have to guess whether zero means "nothing is scheduled" or "the lookup failed". Econ releases especially cluster on specific dates each month, so a 48h window often straddles a dead stretch.

Save data the agent will need to reuse later — across this conversation or across sessions. Use when you discover something worth carrying forward (a resolved ticker, a target address, a user preference, a research subject) so you don't have to look it up again. Stored as a key-value pair scoped by your identifier. Authenticated users get persistent memory; anonymous sessions retain memory for 24 hours. Pair with recall to retrieve later, forget to delete.

Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence — {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and its value is always null — never guessed, never a blended score. Sources: "web" fetches the company's own site (entity.domain required — homepage, /about, /leadership) via fetch_url; "catalog" checks entity_profile (SEC EDGAR; resolved:false for a private company is expected, not a failure); "both" (default) tries both. max_cost (USD, default 0.02, max 0.50) scales how many pages are fetched and refuses up front if it is too small to pay for even one extraction call (floor $0.002) — never silently overspends. A row where every source comes back empty costs nothing: every field is mechanically not_established with NO model call made. For a boolean/derived field (e.g. "does this company sell to healthcare"), the quote only has to SUPPORT the value — a descriptive sentence about customers/products counts, the source need not state the answer verbatim. leadership_page_status ("fetched"|"not_found"|"not_attempted", plus leadership_note) says plainly whether a leadership/team page was actually read, so a named-person field (head_of_sales) coming back not_established is distinguishable from "this company just doesn't publish one" vs. "we never checked". model_output_empty:true means the model returned nothing usable (a transport/budget problem) — every field is not_established for THAT reason, never read as 20 individual "no" judgments. Use with a fixed question + schema across many rows for "Claygent over N companies with a hard cost cap" (composes with batch callers). For picking from a fixed label list instead of extracting open fields, use classify_row (cheaper, one model call).

"What's the ticker for…" / "find the CIK for…" / "what's the LEI for…" / "what's the RxCUI for…" / "look up the ID for…" / "what is X's official identifier" / "who owns X" / "is X a subsidiary of Y" — resolve a user-spoken NAME to the canonical/official identifiers other tools require as input. Use FIRST whenever you have a name but need an ID. SUPPORTED TYPES: "company" (cross-source identity spine: 10-digit CIK + ticker + company_name from SEC EDGAR, legal-entity LEI from GLEIF with parent/ultimate-parent/children ownership when the LEI resolves, and security FIGI from OpenFIGI — by exact ticker map when a ticker is implied, and otherwise by name search, so NON-EQUITY instruments that never have a ticker (municipal and corporate bonds, notes, authority debt) DO resolve here; when a name matches more than one instrument it asserts nothing and returns `figi_candidates` to pick from, which is the correct answer to an issuer name that does not identify a single bond; every identifier is labelled with the source that established it, and an identifier that could NOT be resolved is stated explicitly under `unresolved` rather than omitted — accepts ticker, CIK, ISIN, or company name as input; an ISIN like "CH0038863350" resolves to the LEGAL ENTITY that issued the security via the GLEIF ISIN-to-LEI mapping, covering non-US issuers EDGAR cannot reach), "drug" (returns RxCUI + ingredient + brand from RxNorm + pipeworx://rxnorm/concept/{rxcui} citation; accepts brand or generic name). LEI/FIGI enrichment degrades gracefully — if GLEIF or OpenFIGI is unavailable, the EDGAR identifiers still return. Each call cascades through several lookup endpoints internally — using resolve_entity replaces 2-3 manual lookups.

Create a proactive monitoring subscription to a live-data event stream. Returns the new subscription id. Requires a Pipeworx OAuth account (anonymous + BYO cannot persist subscriptions). Supported types: "sec_8k" (8-K filings matching ticker + item codes — e.g. items:["5.02"] = officer change), "polymarket_edge" (Polymarket↔Kalshi cross-venue mispricings — params:{topic:"fed"}), "fred_series" (new FRED observations — params:{series_id:"UNRATE"}), "patent_grant" (new USPTO grants for an applicant), "clinical_trial" (new/updated ClinicalTrials.gov studies), "form_d" (new SEC Form D fundraise notices — params:{state?, industry?, min_amount?, exemption?}, all optional), "news_keyword" (GDELT keyword news alerts, metadata+link only — params:{query, lang?, domains?}), "job_post" (new public job-board postings — params:{ats?, board_token?} or {domain?}, plus optional title_query/location_query), "tool_diff" (re-runs any read-only tool on a schedule and fires on change — params:{tool, args?, fields[], schedule}), "new_entity" (new business registrations from a state business-entity registry — params:{state:"CO", name_query?, entity_type?}). Delivery channels: feed (always on — pull via recent_alerts or GET registry.pipeworx.io/alerts.json), and optionally email (set delivery:{email:"[email protected]"}) or sms (delivery:{sms:"+15551234567"} — phone must be verified at /account first; 10/day cap).

List the caller's active subscriptions. Returns id, type, params, created_at, last_fired_at, fire_count for each. Use this to review what you're monitoring before adding more or to find an id to cancel.

What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data do you have? — the onboarding entry point for an agent that just connected and wants to know what is worth asking. Returns category-bucketed example questions (company financials, drugs & clinical trials, economics, real estate, prediction markets, weather, government & patents, science & academia, news) — each with the exact tool + argument shape that answers it, drawn from the live catalog of thousands of tools. Call with no arguments for the full spread, or pass `topic` (e.g. "finance", "pharma", "betting") to focus. Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools (ask_pipeworx, entity_profile, compare_entities, etc.).

Cancel a subscription by id. Ownership is enforced — you can only cancel your own subscriptions. The row is deactivated (not deleted) so its historical events stay available via recent_alerts.

"Is it true that…" / "fact check" / "verify the claim that…" / "did X really…" / "was Y actually…" / "confirm or refute" / "true or false" — natural-language claim verification against authoritative sources. Use whenever the agent needs to check whether something a user said is factually correct. Company-financial claims (revenue, net income, cash for public US companies) verify via the structured SEC EDGAR + XBRL fast path with exact percent-delta math; ANY OTHER factual claim (macro statistics, rates, prices, drug data, records) automatically falls through to the grounded pipeline — routed to the right live source, answered with verbatim evidence, then judged. Returns a verdict (confirmed / approximately_correct / refuted / inconclusive / unsupported / could_not_verify), the grounded or structured actual value with pipeworx:// citation, and reasoning. IMPORTANT for callers: could_not_verify means the check did not happen (our LLM or source failed) and carries verification_error{stage,detail} — it is NOT evidence for or against the claim, and must not be shown as one. unsupported means we looked and cover no source for it. Replaces 4–6 sequential calls (NL parsing → entity resolution → data lookup → comparison).

Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model. Default model is Workers AI Llama-3.3-70b (free); pass `_apiKey` to also probe Anthropic (BYO key — you pay Anthropic directly for those calls). Returns per-model {score, confidence, signals, raw_response} + a combined view. Useful for AI-marketing audits, pre-launch brand checks, competitive monitoring.

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).