"SQLite - A Lightweight Database Engine" matching MCP tools:

• update_template_draftA

  FaldaroA

  Save a template’s draft. Both kinds take structured `content` — see create_document_template for the node format; notifications use its EMAIL profile (no image, no pageBreak) — or, for a template still on the legacy HTML engine (check get_template_draft’s `engine`), a `body`; a structured draft refuses body-only writes. Notifications also take subject and recipients; documents also take `settings`. Editing a live template’s draft does not change what sends until publish_template. A document on the SVG facsimile engine (engine "SVG") is edited with edit_svg_template, never here. Requires notification:write or document:write.

  Connector

  Destructive

  API key

• sixta_explain_errorA

  sixta-connectA

  Decode a database error and get the fix and the next step — no connection needed. Paste a MySQL error number (1213, 1062, 1452, 1205…) or a PostgreSQL SQLSTATE (40P01, 23505, 53300…), optionally with the failing statement, and get the proximate cause, the concrete fix, and — when it helps — the SIXTA tool and artifact to go deeper (e.g. a deadlock → paste SHOW ENGINE INNODB STATUS for sixta_explain_deadlock). Use when the user pastes a DB error code or message. Input is analyzed in memory and never stored.

  ConnectorOAuth

• kirk_list_modelsA

  Kirk — Unsupervised Structural Change DetectionA

  Enumerate the model_ids the sealed engine exposes, with the engine sha stamped in-response. Purpose: Discover the model catalog and record the sealed engine sha alongside your inference results. Use when: You are wiring a client for the first time and need model_id values for kirk_score_book / kirk_score_book_batch calls, or you want a machine-readable catalog with attestation. Do not use when: You need per-model hyperparameter detail — those are intentionally not exposed on the customer surface. Capability class(es): C5 (engine sha attested on every response). Path fit: Validation via MCP (this tool). Production integrations run in-process under sealed-engine attestation — same binary sha as this endpoint. Contact Kavara for deployment options. Cost: 0 IU. Free tool.

  ConnectorNo auth

• engine_infoA

  Backtest360A

  Engine version, API contract number, and health. Free (not quota-counted). Call once at the start of a session to confirm the engine is reachable and which contract it serves.

  ConnectorNo auth

• list_compiled_corridorsA

  lr-labsA

  List which treaty pairs, PE families, and compiled-rule counts the LR Labs engine covers, plus the structured-fact schema. Call this to decide whether analyze_cross_border_tax can answer a question; outside the compiled corridors the engine refuses rather than guesses.

  ConnectorNo auth

• get_directory_statisticsA

  Game Dev Outsourcing DirectoryA

  Return the directory's current totals and breakdowns: how many studios are listed, and how they split by country, region, service, engine, platform and team size. Use for any "how many studios..." or "which country has the most..." question, and quote these figures rather than counting search results yourself — they are recomputed from the live database and the counts move.

  ConnectorNo auth

• kirk_verify_engineA

  Kirk — Unsupervised Structural Change DetectionA

  Verify sealed engine identity — returns the sha256 of the running scoring binary. Also serves as a liveness probe against the sealed backend. Purpose: Attest which Kirk build is currently serving scoring calls. Response carries the HOST DEFAULT engine sha (kirk_version). That is the legacy default and is NOT necessarily the engine that will stamp a given kirk_score_* result: each model row in kirk_list_models identifies its own engine, and every scoring response restates it under engine.sha. For a model bound to a non-default engine (kirk-market-orderbook-v1) these differ. Record the per-model value for provenance, not this one. Secondary role: a cheap liveness probe when wiring up MCP. Use when: You want to record engine sha in your own provenance log before capturing scoring output, or you want a cheap liveness check ahead of a larger validation batch. Do not use when: You want a scoring result — this returns identity/liveness only, no entropies. Capability class(es): C5 (cryptographic attestation of engine identity). Path fit: Validation via MCP (this tool). Production integrations run in-process under sealed-engine attestation — same binary sha as this endpoint. Contact Kavara for deployment options. Cost: 0 IU. Free tool. For agent-driven callers, the _cost envelope still reports iu_this_call=0 and the running session totals. Returns: Dict with `status`, `engine`, `env`, and `kirk_version` (the sealed .so sha). A non-2xx response raises; caller sees a clean MCP tool error.

  ConnectorNo auth

• sixta_explain_deadlockA

  sixta-connectA

  Reconstruct a database deadlock from the raw dump — no connection needed. Paste the LATEST DETECTED DEADLOCK section of MySQL's SHOW ENGINE INNODB STATUS, or a PostgreSQL 'deadlock detected' log entry, and get: which transaction held and waited for which lock, the inconsistent lock-ordering that caused the cycle, which transaction was rolled back, and the consistent-ordering / short-transaction / retry fix. Use when the user pastes a deadlock dump or asks 'why did this deadlock'. Input is analyzed in memory and never stored.

  ConnectorOAuth

• healthA

  mcpA

  [META] Liveness + lightweight pipeline stats: uptime, signals in last 1h, current macro regime, classifier backlog. Mirrors REST GET /health with extra context. Pro-gated (per tools/call rule) — use REST /health for unauthenticated liveness.

  ConnectorNo auth

• resize_databaseA

  DockholdA

  Change how much memory an app's managed database gets. Call this when the database is slow or out of memory. db_ram_mb must be one of the sizes get_resource_usage reports under db_ram.steps_mb and fit your database-RAM pool. WARNING: the database restarts briefly to apply the new size, so the app loses its database connection for a few seconds. Only works if the app has a managed database.

  ConnectorNo auth

• get_scan_statusA

  mcp-serverA

  Check whether a queued scan has completed. Lightweight polling endpoint — call every 3-5 seconds with the `scan_id` returned by `submit_scan`. Scans typically complete in 5-15 seconds. When `status` is 'complete', call `get_scan_results` for the structured findings. When 'failed', surface the `error` field to the user.

  ConnectorNo auth

• get_engine_schemaA

  ReefAPIA

  COMPACT overview of ONE engine: every action with its description, required params and what it returns — but NOT the full param detail (kept lean so a 90-action engine stays token-cheap). Call this after search_engines to pick the right ACTION, then get_action_schema(engine, action) for that action's full params before call_engine.

  ConnectorNo auth

• get_catalogA

  ReefAPIA

  The FULL ReefAPI catalog — EVERY engine with its one-line title, grouped by category. This is the whole menu (≈ a few thousand tokens); SCAN IT AND PICK THE BEST ENGINE YOURSELF. You are an LLM, so you match the user's intent semantically — across ANY language, typo, or phrasing — far better than a keyword search can. Use this whenever search_engines didn't surface the right engine (or to be sure you didn't miss a better one). After you pick: get_engine_schema(engine) -> get_action_schema -> call_engine.

  ConnectorNo auth

• healthA

  n0brainsA

  [META] Liveness + lightweight pipeline stats: uptime, signals in last 1h, current macro regime, classifier backlog. Mirrors REST GET /health with extra context. Pro-gated (per tools/call rule) — use REST /health for unauthenticated liveness.

  ConnectorNo auth

• explain_planA

  sqlai.dev SQL VerifierA

  Return the engine-native query plan for a query (SQLite: EXPLAIN QUERY PLAN) plus full-table-scan warnings. Use it to check whether an index would be used before recommending one. Example: "SELECT * FROM orders WHERE status=?" on an unindexed column → plan ["SCAN orders"], warning about the full scan.

  ConnectorNo auth

• set_app_storageA

  DockholdA

  Give an app storage that survives restarts and deploys, or grow the storage it already has. Call this when the app has to keep files: a SQLite database file, uploads, or anything the user expects to still be there tomorrow. The app reads and writes the folder at the path in the DATA_DIR environment variable, which Dockhold sets; anything written outside DATA_DIR is scratch space and is lost on the next restart. size_gb must be one of the sizes get_resource_usage reports under volume.steps_gb and has to fit your storage pool, which is the same pool a managed database draws on, so call get_resource_usage first. Storage can grow but never shrink. Three things to tell the user before calling this: an app with storage runs as a single copy, it cannot have scheduled tasks, and from now on each deploy stops the running version before the new one starts, so the app is unreachable for a few seconds. Write the app to save its files when it receives SIGTERM.

  ConnectorNo auth

• list_sessionsA

  mumoA

  List the caller's deliberation sessions, optionally filtered by status. Most useful for agents managing multiple concurrent sessions — use `status: 'ready'` to find sessions awaiting your next round. Returns a lightweight list (no response bodies); call `get_session` for full content.

  ConnectorNo auth

• delete_databaseA

  mcpA

  Deletes a managed Postgres database and its underlying VM. Pass the numeric database id from list_databases. This cannot be undone.

  Connector

  Destructive

  No auth

• list_exchangesA

  TradeTi.me — Market HoursA

  List the tracked stock exchanges as lightweight summaries (id, name, city, country, timezone, region, importance). Optionally filter by region (e.g. "Asia", "Americas", "Europe"). Use this to discover valid exchange ids.

  ConnectorNo auth

• upgrade_to_haA

  mcpA

  Turns an EXISTING, running single-machine managed Postgres or ClickHouse into a THREE-machine highly available cluster, in place, keeping the data and the same username, password and database name. Use this when the user has a live database and wants it to survive a machine or host failure: they do NOT have to create a new one and migrate by hand. How it works: a full backup is taken first (kept whatever happens), the cluster is built alongside, the data is copied in and verified by counting both sides, and only then does the database's address move to the load balancer. The original machine is left running and untouched throughout, so a failure changes nothing and the user is never without a database. SAY THREE THINGS TO THE USER AND GET A YES BEFORE CALLING: (1) COST, it becomes three machines behind a load balancer instead of one, so roughly 3x the hourly rate, and the old single machine keeps billing until they delete it; (2) WRITE LOSS, anything written to the old machine during the copy is not carried over (see acknowledge_write_loss); (3) THEY MUST REPOINT THE APP afterwards, the connection address changes and nothing redeploys their app for them. Takes about 20 minutes and returns immediately; poll list_databases / list_clickhouse_databases until the address changes. Requires a payment method: high availability is not available on the no-card trial. ⛔ CLICKHOUSE ONLY, a FOURTH thing to say: after the upgrade every table has to use a REPLICATED engine. The existing tables are converted for them as part of the copy, but any NEW `CREATE TABLE ... ENGINE = MergeTree` is refused from then on (ClickHouse error 56) and has to be written `ENGINE = ReplicatedMergeTree`. It is refused rather than accepted because a plain MergeTree on three machines replicates its schema and not its rows, which would leave two of the three answering with an empty table and no error. If their app ships plain-MergeTree migrations (Plausible, PostHog and Langfuse all do), those migrations will fail after the upgrade and they should stay on the single machine. For the app tier rather than the database, use upgrade_to_cluster instead.

  Connector

  Destructive

  No auth

• get_softwareA

  PeppolStatusA

  Get one software product (Market) One engine of the software library: the same row the list returns (product metadata, host count per observed role, first/last seen, the compliance signal and the host-count trend) plus the catalogue version and generation stamp. `engine` is a catalogue engine slug as published in `engine` on the list; an unknown slug is a 404. Beyond the list row it also returns `advisory_list[]` (issue #798): every live advisory of the engine's lanes with its id, normalized severity, CVSS score, summary, url and publication stamp, newest first. Null when no lane of the engine has an advisory feed; `[]` when it has one and upstream has published nothing. Market tier.

  ConnectorNo auth