"Keep a Changelog" matching MCP tools:

• eurostat_query_dataset

  eurostat-mcp-server

  Fetch statistical data from a Eurostat dataset with dimension filters. Returns decoded observations with dimension codes and labels, numeric values, and status flags (e.g., "p" = provisional, "e" = estimated). Call eurostat_get_dataset_info first to discover valid dimension codes and values. Apply filters to keep the result set manageable — large unfiltered queries may trigger an async response error. Use filters.geo for specific country/region codes, or geo_level for NUTS hierarchy filtering (mutually exclusive). Use last_n_periods for the N most recent periods without knowing the end date.

  Connector

• unulu_update_site

  unulu

  Update an existing site. All fields are optional — only provided fields are changed. Links replace the entire array (omit to keep existing). Before updating, always call unulu_get_state first to read the current links and their ids — do not guess link ids. Authorization depends on site lifecycle: X-Claim-Token header for ephemeral (pre-claim) sites, X-Edit-Token header for claimed (post-claim) sites. If neither token is available and the site is claimed, use requestEditAccess to obtain an edit_token. If you created the site in this conversation, you already have the claim_token — use it directly. Returns the full updated site state. Keep iteration fast — apply changes immediately without re-confirming minor edits unless ambiguous. Accepts a site ID, a full URL (e.g. https://abc123.unu.lu), or a bare hostname (e.g. abc123.unu.lu).

  Connector

• cti_get_brief_template

  website-search

  Get Lenny Zeltser's CTI one-page executive brief template. Standalone variant of `cti_get_template` for callers that only want the brief without the long-form report. This server never requests your campaign or threat-intel notes and instructs your AI to keep them local—templates and guidelines flow to your AI for local analysis.

  Connector

• perspective_await_job

  Perspective AI

  Long-polls a perspective-design job (started by perspective_create, perspective_respond, or perspective_update) and returns either its terminal result or another "pending" envelope to keep polling. Behavior: - Read-only — observes a running design job. Safe to call repeatedly. - Errors with "Unknown job_id" if no such job exists, or "job_id does not belong to a perspective design workflow" if the id is for a different kind of job. Workspace and perspective access are re-checked on every call. - Each call blocks up to wait_ms (default 30s, min 1s, max 45s). On timeout, returns status "pending" with a progress_cursor — pass it back on the next call to skip already-seen progress events. - Terminal status is "ready" (outline generated; share_url/direct_url/preview_url populated) or "needs_input" (follow_up_question populated). Failures surface as "Design job failed: ..." with the underlying message. When to use this tool: - Immediately after perspective_create / perspective_respond / perspective_update returns a job_id. - Re-polling after a previous call returned status "pending" (pass the returned progress_cursor back). When NOT to use this tool: - You don't have a job_id yet — call perspective_create / perspective_respond / perspective_update first. - Inspecting a finished perspective's config — use perspective_get.

  Connector

• rating_get_sheet

  website-search

  Get Lenny Zeltser's cybersecurity-writing rating sheet(s) so your AI can apply the rubric. Returns the structured rubric (groups, items, scoring bands) WITHOUT computing a score. Use `rating_score_writing` if you also want a numeric score, gap analysis, or rubric-anchored feedback. This server never requests your draft and instructs your AI to keep it local—rating sheets and scoring instructions flow to your AI.

  Connector

• purchase_report

  mcp-server

  Start a purchase of the full paid SEO remediation report for a COMPLETE scan ($8.99). Returns a Stripe `checkout_url` — payment CANNOT be collected through this tool. AUTONOMOUS FLOW: after calling this, do NOT stop and wait for a new user instruction. (1) Show the user `checkout_url` and ask them to complete payment in their browser. (2) Then poll `get_purchase_status` with the same scan_id about every 15 seconds: while `paid` is false the user hasn't finished — keep waiting (poll for up to a few minutes). (3) Once `paid` and `runbook_ready` are both true, call `get_remediation_plan` once, save the returned markdown to the file it names, and begin the remediation automatically — no further prompting needed. If this call returns already_purchased=true, skip the wait and go straight to get_remediation_plan.

  Connector

• add_text

  cnvs.app

  Create a NEW text node, or update an existing one (pass the same `id` to overwrite content/position in place — preferred over creating a duplicate). Supports cnvs markup (Markdown-ish) and Mermaid diagrams in the content. When using Mermaid, the ENTIRE content of this text node must be a single Mermaid diagram (one ```mermaid fenced block and nothing else — no heading, no prose before or after). If you need prose + a diagram, create two separate text nodes. `postit: true` renders as a yellow sticky; `diagram: true` renders as a framed box (2px border in the text colour, centred text) — the two are mutually exclusive. Coordinates are in board-world pixels, +x right, +y DOWN; pick a spot that does not overlap existing items (check `get_preview` first). Default width auto-fits content up to ~320 px; pass `width` for explicit wrapping (160–4096). Keep content under 100 000 chars.

  Connector

• ir_get_brief_template

  website-search

  Get Lenny Zeltser's IR one-page executive brief template. Standalone variant of `ir_get_template` for callers that only want the brief without the long-form report. This server never requests your incident notes and instructs your AI to keep them local—guidelines flow to your AI for local analysis.

  Connector

• update_blueprint

  governance-platform

  Update an existing Blueprint's configuration in place. Only fields you pass are updated; fields you omit keep their current values. To clear a list field (e.g. remove all rules), pass an explicit empty list []. Existing API keys for this Blueprint are preserved — agents using those keys continue working after the update. Ownership stamps are also preserved; you cannot transfer Blueprint ownership. The workflow_name itself cannot be renamed. To rename, create a new Blueprint with the new name and delete the old one. Different from create_blueprint: create_blueprint creates a new Blueprint and mints a fresh API key. update_blueprint modifies an existing one and returns no new key. Args: api_key: GeodesicAI API key (starts with gai_) workflow_name: Name of the Blueprint to update (must already exist) customer_name: New customer/project name. Pass None to keep current. mode: "observe" or "enforce". Pass None to keep current. extracted_fields: New list of agent-extracted fields. Pass None to keep current; pass [] to clear. derived_fields: New list of platform-derived fields. None or []. derivation_rules: New list of derivation rules. See blueprint_guide prompt for schema. None or []. formal_constraints: New list of constraints. See blueprint_guide prompt for schema. None or []. semantic_checks: New list of semantic checks. None or []. require_math: Override math validation flag. None to keep current. require_consistency: Override consistency flag. None to keep. require_coherence: Override coherence flag. None to keep. require_provenance: Override provenance flag. None to keep. require_high_assurance: Override high-assurance flag. None to keep. enable_anomaly_detection: Override anomaly flag. None to keep. enable_drift_tracking: Override drift flag. None to keep. Returns: status: "ok" | "ERROR" blueprint: workflow_name that was updated fields_changed: list of config keys that were modified field_count: new total of extracted + derived fields rule_count: new total of derivation rules constraint_count: new total of formal constraints

  Connector

• ask_human

  humanMCP — kapoost

  Ask kapoost a question that requires human judgement. Returns an ID — poll fetch_answer(id) later to retrieve the response. Use sparingly: only when the answer materially affects your task and is not derivable from the content. Examples: 'czy moge cytowac ten wiersz w komercyjnej publikacji?' / 'co inspirowalo metafore w Y?'. Max 1000 chars in question, max 500 in context. Open to any caller — rate-limited to 5 per hour per IP to keep the queue useful.

  Connector

• faostat_dataframe_query

  faostat-mcp-server

  Run a single-statement SELECT against the canvas tables staged by faostat_query_observations and faostat_commodity_profile (table names look like faostat_xxxxxxxx). Use this for cross-country and cross-item aggregation, GROUP BY rankings, joins, and time-series analysis over the full result set the inline preview only sampled. Standard DuckDB SQL — joins, aggregates, window functions, CTEs all work. Read-only: writes, DDL, DROP, COPY, PRAGMA, ATTACH, and external-file table functions are rejected; system catalogs (information_schema, sqlite_master, duckdb_*) are denied — list staged tables via faostat_dataframe_describe. Every row carries its data-quality `flag` (A=Official, E=Estimated, I=Imputed, …) — keep it in projections and honor it in interpretation.

  Connector

• taste

  Pane

  Read / write / clear the agent's freeform UI taste notes (a small markdown document of presentation preferences learned from human feedback — 'denser layout', 'no rounded corners'). ONE tool with an `action` enum: get | set | clear. Call `get` BEFORE generating a pane so prior feedback shapes the output; `set` does a whole-document replace (not append). Keep entries about UI/presentation only.

  Connector

• demand.create_watch

  iwant.fyi - demand-side commerce

  Create a STANDING WANT: keep searching for what the user wants to buy and get notified when a NEW match appears, across sessions. Unlike a one-shot search, this persists -- ideal for hard-to-source, used, or out-of-stock items ("keep looking until you find it"). Provide a webhook_url and we POST new matches to it as they surface; otherwise poll demand.list_watches. Same query shape and enforced constraints as demand.search.

  Connector

• mu_preview_mockup

  mu

  See the mockup BEFORE creating any product — nothing is created or sold, and it costs no credits. Renders the design on the real garment (Printful) when the kind supports it (source: "printful"), otherwise a clean MU product card (source: "card"), and returns a durable preview image URL. Optionally pass `position` (front-print DTG apparel only: tee / tee_white / hoodie / crewneck / tank / long_sleeve_tee) to preview a custom print placement — passing the SAME position to mu_create_product prints exactly what you previewed (WYSIWYG). Usually answers in 10-45s; if it returns status="processing", call this tool again with the returned `preview_id` to keep waiting. Rate limit: 30 previews/hour. Requires `Authorization: Bearer <api_key>`.

  Connector

• fetch_page

  mrmarket.ai

  Fetch the NEXT page of a large query_data result — FREE (zero credits, runs no new query). Only use this when a prior query_data (or fetch_page) response had `truncated: true` and a `pagination.next_cursor`. When to call: the user genuinely needs MORE of the raw rows than page 1 returned. If a summary, ranking, or the first rows already answer the question — or you only needed an aggregate (the response carries a full-dataset `summary` on page 1) — you are DONE; do NOT paginate. Pass the cursor string from `pagination.next_cursor` VERBATIM — do not edit or truncate it. Keep calling fetch_page with each new `next_cursor` until it is null. Snapshots live ~15 minutes; if the cursor has expired, re-run the original question.

  Connector

• calls_wait

  DialogBrain

  Block until a voice call ends (status changes from 'active') or timeout elapses. Returns ended=true with final state when the call has ended; ended=false on timeout (re-issue to keep waiting). The returned state includes `outcome` so callers can branch on pickup vs. no-answer (answered/no_answer/busy/declined/failed/unknown). Default timeout 90s; cap 110s — bounded by nginx proxy_read_timeout 120s on /mcp.

  Connector

• get_auth_session

  agentView

  Polls the status of a login session created by create_auth_session. Use this after create_auth_session; poll every 2-3 seconds until the status is no longer 'pending'. Do not use this for any other purpose. Returns one of three states: 'pending' (user has not logged in yet — keep polling), 'active' (login succeeded; tokenExpiresAt is an ISO 8601 timestamp for when re-authentication is required. For security the raw bearer token is intentionally not returned over MCP, so keep using your session_request_id on protected calls), or 'expired' (login window or token timed out — call create_auth_session again). When status is active the current MCP session is automatically authenticated; you can call protected tools immediately.

  Connector

• legal_list_laws

  Lawbster

  List available laws, regulations, and court decisions in the database. Returns abbreviation, title, source type, jurisdiction, document kind, and version date for each entry. Unfiltered listings can contain thousands of entries; pass a search term or source_type to keep responses focused. Useful for discovering valid law abbreviations to use as filters in legal_search. Found a relevant law? Use legal_get_toc to browse its structure. NOT an existence check for a specific law: EUR-Lex entries store the official long title, so searching by common name or number can miss laws that ARE in the corpus. To verify a law exists, use legal_lookup with a citation or legal_search with a topic instead.

  Connector

• emem_at

  emem — Earth memory protocol

  One-shot multi-band recall at a place (or lat/lng). Defaults to emem's standard at-a-glance band set; pass `band` / `bands` to override. Polygon-resolved places stay at the centroid by default (`n_cells: 1`) to keep multi-band calls cheap — pass `n_cells: 2..=64` to fan out. When to use: Use when the user names a place and wants the standard situational readout (vegetation + elevation + landcover + recent weather) without picking bands. Polygon-aware: `place` that resolves to a polygon (park, lake, district) lands at the centroid unless `n_cells` widens it. For a single band, use the domain-specific shortcuts (emem_ndvi, emem_air, …) or emem_recall directly.

  Connector

• undo

  reassign

  Undo — revert, roll back, take back, or cancel the last — recent schedule/confirm_schedule creates or a write_events / delete_events batch, using the `undoToken`s they returned. Pass `tokens`. Each works only while still active and within its 30-minute window; a schedule/confirm_schedule token deletes the event it created, a write_events / delete_events token reverses the whole batch (deletes what it created, restores what it changed/removed), and a `batchUndoToken` from a multi-event schedule call removes the events that batch auto-created and voids its open proposals (times you confirm from proposals keep their own undo tokens). Returns per-token `results`.

  Connector