Myriade MCP Server

Ask a natural language question about a database using Myriade's data analyst agent. The agent will explore the database schema, search the catalog, run SQL queries, and analyze the results to answer your question. Use this for complex analytical questions that require multiple steps; for simple schema lookups or direct SQL, prefer the other tools. The run executes in the background as a regular Myriade conversation (visible in the web UI). If it finishes quickly the answer is returned directly; otherwise the tool returns ``{"status": "running", "conversation_id": ...}`` — poll myriade_get_answer with that id to retrieve the result. Long analytical questions are expected to take several minutes. Note: the agent has access to catalog write operations (create/update assets, tags, terms) — it may modify catalog state to record findings. It can also read, create and edit reports (ask it to "write a report on ..." or "update report <id> with ..."). Use myriade_query directly for strictly read-only inspection. Requires AI_PROVIDER and the corresponding API key (e.g. AI_PROVIDER=anthropic + ANTHROPIC_API_KEY).

The organisation's audit value map: every domain (key, name, its document, zone count), every active zone (slug, name, domain, verdict, gain, star, last verified, its document) with its levers and their class (quick_win, quick_action, waiting, project, long_term), the domain keys zones use without a domain document, and the zone or domain documents whose block could not be projected (with the error to fix). Read zones and levers in full with myriade_audit_read_zones / myriade_audit_read_levers, a zone's narrative with myriade_read_report (the uuid inside <DOCUMENT:uuid>).

Levers as their page shows them: every field, the class, the human follow-up (status, assignee, note) and the dated figures behind each. An id that is no lever on the map comes back under errors. A query is shown only on connections you may read.

Zones as their page shows them: the record from the ```zone block, the dated figures recorded on the zone, its levers in short (id, name, stage, class, follow-up, estimate) and its document. A slug with no active zone comes back under errors. A figure's query is shown only on connections you may read (``restricted`` otherwise).

Record a dated figure backing a zone (or one of its levers), linked to the query that computed it, on a connection you may read. Recording the same label again on the same zone or lever replaces the figure.

Create a lever in a zone of the audit map, or update one by its id (an argument you omit keeps its value). Cite the returned id as <LEVER:id> in the zone document. Its class is computed from effort × gain_delay × timing; the follow-up (status, assignee, note) is set on its page.

Create a report owned by the caller, private until shared. Share it with myriade_set_report_access(visibility="everyone"): an audit zone or domain document joins the map only once organisation-wide.

Replace text in a report, as the caller (a version is recorded). Read it first with myriade_read_report. A published report is editable only by its owner or an org admin.

Retrieve the result of a myriade_ask run. Returns ``{"status": "completed", "answer": ...}`` once the analyst agent has answered, or ``{"status": "running"}`` while it is still working — keep polling in that case. ``{"status": "failed"}`` / ``{"status": "quota_exceeded"}`` carry the run's error. ``{"status": "no_answer"}`` means the run is gone without a recorded answer (agent stopped silently, or the server restarted): start a new myriade_ask run.

Get a monitoring check (name, SQL, severity, cadence, status) and its most recent run results, newest first. On governed databases the SQL and evidence rows are redacted unless you manage the database or authored the proposal.

Get detailed information about a specific database connection. Returns information about the database including its name, engine type, description, write mode, and any AI memory notes.

Re-execute a saved Myriade query and return fresh results. The query's SQL always re-runs under the caller's governance policies (table permissions, column masking) — results are never served from Myriade's cached snapshot. Prefer this over myriade_query for recurring metrics (dashboards, cockpits): the SQL stays governed in Myriade instead of travelling through prompts. Write statements are blocked. Returns up to 50 rows with column metadata, same shape as myriade_query.

Get the column-level schema for a specific table. Returns column names, data types, and descriptions for the table, plus the SQL `dialect` to use with myriade_query on this database. When the name is ambiguous across schemas, the candidates are returned under `matches` instead — pass `schema_name` to pick one. Raises if the user has no access to the table under governance.

List databases configured in Myriade (paginated, sorted by name). Returns paginated database connections with their IDs, names, engines, and descriptions. Use the database ID with other tools.

List or search reports (documents) written in Myriade. Without ``query`` returns the most recently updated reports first; with ``query`` returns the best matches first. Only reports the caller may see are returned. Read one with myriade_read_report.

List tables in a database (paginated, sorted by database/schema/name). Returns a flat, paginated list of tables. Each item has database_name, schema, and name fields. The response's `dialect` is the SQL dialect to use with myriade_query on this database.

Snapshot of a database's monitoring board: check count, standing alerts (open / acknowledged / known) with their headlines, recent notifications and triage notes, followed by the open alerts as JSON — each with its investigation and evidence while they fit, then as listing lines, with ``shown`` / ``total`` / ``detailed`` saying which. Alert ids feed myriade_triage_alert; check ids feed myriade_get_check. Investigation details are redacted unless you manage the database.

Propose a monitoring check for the user to review in Myriade. This creates a PROPOSAL, never an active check: nothing runs until a database owner or org admin accepts it in the app. The SQL is test-run once under your governance context to validate it. Contract for ``check_sql``: it MUST return rows ONLY when something is wrong (zero rows = healthy) and use relative time (``now() - interval``), never absolute dates. Minimum cadence is 5 minutes. Names are unique per database — read myriade_monitoring_overview before proposing a near-duplicate.

Execute a read-only SQL query against a database. Write the SQL in the dialect of the target database's engine — see the `dialect` field returned by myriade_list_tables and myriade_get_table_schema, or the engine in myriade_list_databases. Write operations (INSERT, UPDATE, DELETE, DROP, etc.) are blocked. Returns up to 50 rows of results with column metadata. Successful queries are saved in Myriade; the response's `query_id` can be replayed later with myriade_get_query_results without resending SQL.

Get detailed information about a catalog object (table, column, schema, or glossary term — assets and terms share one id space). Returns the asset's description, tags, status, columns (for tables), sample data, parent hierarchy, and activity feed; for a glossary term, its definition, synonyms, related terms, and activity feed.

Read a report's full markdown content. Applies the same visibility rule as the web app; a report the caller may not see returns a "not found" error. Edit it with myriade_edit_report, or have the analyst agent rework it with myriade_ask.

Propose a catalog change for the data team to review (no edit rights needed). Creates a reviewable suggestion routed to the asset's reviewers. Does NOT change the published catalog until approved. Use this instead of ``myriade_update_asset`` when you lack edit rights or are not confident enough to write directly.

Get sample rows from a table to understand the data. Returns a random sample of up to ``limit`` rows (max 20).

Search the data catalog for tables, columns, or terms by name/description. Uses fuzzy matching and full-text search. Keep queries short (1-2 words) for best results.

Change who can read a report: visibility (its owner only) and web publication (its owner or an org admin).

Triage an alert (requires manage access: database owner or org admin). - ``resolve``: the underlying problem is handled or gone. - ``acknowledge``: keep it standing with a ``statement`` of what is happening — only for a situation that may worsen. - ``dismiss``: false positive / expected; refused while the check still trips (it would just respawn). - ``snooze``: silence for ``hours`` with a ``statement``; reopens by itself if the check still trips afterwards. - ``reopen``: send a parked alert back to "needs action" with a ``statement`` of what is no longer covered.

Update a catalog asset's documentation (requires edit rights). - ``description`` replaces the existing description (auto-sets status to "draft" if status is null). - ``tag_ids`` replaces all tags (accepts names or UUIDs; auto-creates missing tags). - ``status`` is "draft" (needs review) or "published". Only use "published" with high confidence. Use ``myriade_request_catalog_change`` instead when you lack edit rights or are not confident enough to write directly.

Rename a report (an audit zone takes its document's title).