"Exploring GraphRAG and HybridRAG" matching MCP tools:

• goal-add-criterionA

  Planner (proof-of-done)A

  Append an acceptance criterion to a goal. The text must describe an observable check over an artifact (e.g. "GET /api/health returns 200 with {status:ok}"), not a subjective approval. Each criterion has a class: pre-merge (default — proved in CI / by attached evidence) or post-deploy (proved by an executable probe against the deployed prod instance). A post-deploy criterion MUST carry probeSpec {method, url, expect:{http_code, body:{field: expectedValue}}} — the request the runner sends and the answer it must get; without it the call is rejected with error=probe_required. Passing probeSpec alone implies probeClass=post-deploy. Set visualEvidenceSuggested=true only when adopting visualAcSuggestion from goal-create, goal-get, or the ready_for_work advisory returned by goal-update; it remains an ordinary AC. Grove mode: AC (class and probe included) can only be added while goal is in backlog, except accepting a visual advisory in ready_for_work: that starts a direct checking_ac recheck, without intermediate backlog. Other edits are frozen once started; quality linter blocks high-severity issues. Standard mode: AC editable until goal is closed, linter is advisory. Returns criterion id, position, text, probeClass, probeSpec and any quality findings.

  ConnectorNo auth

• kirk_demo_tradingA

  Kirk — Unsupervised Structural Change DetectionA

  Runs a curated demonstration of Kirk on a trading example. Zero arguments. Returns real Kirk output against the same sealed engine that customer callers hit. Free, rate-limited. First-time users: call this to see what Kirk does before signing up. Purpose: Score n=30 jittered L2 snapshots per market regime (stationary vs stressed) through the sealed engine and surface the per-regime score-distribution statistics (mean, sd) plus the z-separation between the two distributions in pooled-sd units. Also carries a representative canonical book pair so callers see two concrete scores alongside the distributions. Use when: You are a first-time caller exploring what Kirk does. You want a zero-friction "what does the output look like" experience against real sealed-engine attestation. Do not use when: You are scoring your own data — use ``kirk_score_book`` or ``kirk_score_book_batch``. This tool's input is a fixed synthetic representative pair, not a market feed. Capability class(es): C2 (variable-universe cross-section entropy scoring) demonstrated end-to-end against the sealed engine. Path fit: MCP demonstration surface only. Cost: 0 IU. Rate-limited 3/hour per IP. Returns: Dict with per-regime ``stationary`` and ``stressed`` blocks (each: ``mean``, ``sd``, ``n``, ``kirk_version``), ``z_separation`` (pooled-sd distance between the two regime distributions), ``representative_pair`` (canonical un-jittered ``stationary_score`` / ``stressed_score`` plus ``book_summaries``), ``interpretation_hint``, ``provenance``, and ``synthetic_representative`` flag.

  ConnectorNo auth

• get_leadproof_evaluation_pathA

  LeadProof Sales AgentA

  Use first when a buyer is exploring LeadProof without supplying workflow data. Returns the official no-purchase sequence: buyer guide, fictional example audit, browser-only calculator, public workflow tests, and no-card trial. For a scored workflow diagnosis, use audit_lead_workflow; for replay testing, use get_leadproof_replay_trial; for paid checkout, use get_leadproof_checkout only after authorization.

  ConnectorNo auth

• exploreA

  ThinAir GeoA

  BROWSING / DISCOVERY search — administrative places (cities, neighbourhoods, boroughs, counties, regions) near a location. Use this when the user is exploring a REGION rather than looking for a specific category. Supports population filtering ('cities > 100k'), ranking by significance or distance, and layer filtering (locality / neighbourhood / borough / county / region). Venues, addresses and streets are NOT served here — for venues and POI categories (gas, food, charging, etc.) use `search_places` instead. Each result carries its distance in the caller's units and a bearing from the center.

  ConnectorOAuth

• search_entitiesA

  Cito APIA

  Browse/search teams, players, tournaments, events, fighters with type filter and pagination. When to use: - Typeahead / pickers - "List teams matching…" - Exploring entities without committing to one ID - UFC fighter lookup by name/nickname (uses /ufc/search + client re-rank) Prefer over resolve_entity when the user wants a list. Prefer resolve_entity when chaining one name into a profile tool. Do not use when: fetching a known entity profile — use team_profile or player_profile. UFC: with q set, results are ranked (exact name > multi-token match > nickname). "Jon Jones" should return jon-jones first — never the generic P4P list. Parallel-safe: yes. Upstream cost: 1–3. Example: { "game": "ufc", "q": "Jon Jones", "type": "fighter", "limit": 10 }

  ConnectorOAuth

• goal-add-criterionA

  Planner MCP — provable "done" for AI agentsA

  Append an acceptance criterion to a goal. The text must describe an observable check over an artifact (e.g. "GET /api/health returns 200 with {status:ok}"), not a subjective approval. Each criterion has a class: pre-merge (default — proved in CI / by attached evidence) or post-deploy (proved by an executable probe against the deployed prod instance). A post-deploy criterion MUST carry probeSpec {method, url, expect:{http_code, body:{field: expectedValue}}} — the request the runner sends and the answer it must get; without it the call is rejected with error=probe_required. Passing probeSpec alone implies probeClass=post-deploy. Set visualEvidenceSuggested=true only when adopting visualAcSuggestion from goal-create, goal-get, or the ready_for_work advisory returned by goal-update; it remains an ordinary AC. Grove mode: AC (class and probe included) can only be added while goal is in backlog, except accepting a visual advisory in ready_for_work: that starts a direct checking_ac recheck, without intermediate backlog. Other edits are frozen once started; quality linter blocks high-severity issues. Standard mode: AC editable until goal is closed, linter is advisory. Returns criterion id, position, text, probeClass, probeSpec and any quality findings.

  ConnectorNo auth

• workspace_setupA

  ZeroWidthB

  Creates folders for the work someone described, rooms linked to those folders (with your first message in each, the concrete next step), and starting pieces filed inside. Records what the workspace is for, which orders what home offers first. Use it once you know what they're working on, typically near the end of setting a workspace up. Say in one sentence what you're setting up and call it; the approval card lists the folders, rooms, and pieces, so don't list them in words too. Every workspace already has a General room, so don't recreate it. May return needs_confirmation; then wait for approval. Starting shapes by kind of work (adapt, drop, or combine; name everything after what they told you): - process_redesign: a folder per process being changed ("Claims intake redesign"). Pieces: a Compass page with pageType WORKFLOW describing how it works today, a Napkin diagram of current and proposed steps, a doc for the change plan. Room: "<process> redesign". After setup, offer a Ledger expectation for the metric they want to move. - research: a folder per study or question. Pieces: a research-plan doc (question, who, method), a synthesis doc. Room: "<topic> research". After setup, offer a Prism field for the question. - ai_design: a folder per AI feature. Pieces: a spec doc (what it does, for whom, what good looks like), a Caliper dataset for test cases. Room: the feature's name, with the flow in it once one exists (file an existing flow via existing). After setup, offer to scaffold the flow and a rubric. - knowledge: a folder per domain. Pieces: Compass pages for the main topics. Room: "Ask about <domain>". - exploring: usually nothing beyond their priorities and the General room; offer one small first thing instead. Priorities are Compass pages made with compass_pages_create before this, not pieces here; name folders after the work that moves them.

  Connector

  Destructive

  No auth

• legal_search_patents_by_keywordA

  DataNexus MCPA

  Search patents by keyword across EPO, USPTO, or WIPO. Read-only. No side effects. Idempotent. Returns up to 10 matches. keywords: Search terms describing the invention e.g. neural network image classification. Required. jurisdiction: One of EP, US, or WO. Optional. Default EP. date_from: Earliest filing date in ISO 8601 format e.g. 2020-01-31. Optional, defaults to no lower bound. Returns patent numbers, titles, and filing dates. Use this when finding prior art or exploring a technology landscape without a specific number. Use legal_fetch_patent_by_number instead when you have the patent number already. Verified source: EPO OPS + USPTO. 24-hour cache. If this tool's response does not serve the user's need, call report_feedback with feedback_type="agent_gap", tool_id="legal_search_patents_by_keyword", intended_query="{what the user needed}", gap_description="{what was missing or wrong in the result}".

  ConnectorNo auth

• get_clueprintA

  CluesoA

  Fetch clueprint data. Use `include` to control how much you pull back: - include="metadata": just the clueprint's name/description/tags/visibility/thumbnail. - include="tree": metadata + the full file tree (path, mime_type, and size per entry). Call this first when exploring an unfamiliar clueprint. - include="files": the contents of the files listed in `file_paths` (no metadata — call include='tree' first if you also need metadata). Text inline, binary as presigned GET URLs. - include="all": metadata + the file tree + the contents of every file in the clueprint (use sparingly on large clueprints). Every read is logged for the workspace's recents. Pass use=true ONCE, when you start building a project from it: that counts the use (the clueprint's use count, apply analytics); add project_id when the project already exists.

  ConnectorNo auth

• add-transaction-commentA

  OsomeA

  Post a comment on a transaction as the signed-in user, starting the transaction's conversation if it has none. Every call adds a new comment, so don't repeat a call that succeeded. Returns conversation, totalCount, addedMessage when the conversation already existed, and messages: the latest 20 comments, oldest first, which limit, createdAfter and createdBefore can change. Requires the company:documents:write scope; writes are rate-limited per user. Use get-transaction-conversation to read without posting.

  ConnectorOAuth

• postkey_x_statusA

  Postkey: Instagram DM Automation and Comment-to-DMA

  Postkey: Says whether X is ready for this profile (ready, and what is missing), and where this profile stands: how much of each limit is used (rolling hour and 24 hours), whether X actions are paused and why, the STOP count, the profile's time zone and quiet hours, the saved reply counts, the last 10 actions (ids and times only), and a plain list of what this toolkit does and does not do. Use it to see whether X is set up and why answers are wait or deny; a single action is checked with postkey_x_check_before_send. If ready.ok is false, X is not set up for this account and the answer says what is missing. These X tools send nothing to X and no send tool exists (there is no postkey_x_send_dm, postkey_x_post or postkey_x_reply): you reply or post on X with the customer's own X access. Postkey itself only publishes posts the person schedules in Postkey to their connected X account; it never replies, likes, follows, reposts, sends DMs or reads timelines on X. If postkey_x_check_before_send is not available, this connection was not given X access; the person can reconnect and tick "X: ask Postkey before my agent replies".

  ConnectorOAuth

• list_dropsA

  Real Real GenuineB

  [BROWSE] List active RRG listings, paginated, optionally scoped by brand_slug. Use when exploring the catalogue without a specific item in mind. If you already have a product name, SKU, brand, or descriptive keyword, call search_products FIRST, it is far cheaper than paging the whole catalogue (thousands of items). Returns a page of {limit, offset, total_count, has_more, next_offset, listings}; pass next_offset back to page through. Each listing has title, price in USDC (the exact wallet charge), listPrice (the price and currency on the brand store, when known), edition size, and remaining supply. Live on-chain minted count is in get_drop_details, not here. Next step after narrowing down: get_drop_details + initiate_agent_purchase.

  ConnectorNo auth

• list_dropsA

  Real Real GenuineB

  [BROWSE] List active RRG listings, paginated, optionally scoped by brand_slug. Use when exploring the catalogue without a specific item in mind. If you already have a product name, SKU, brand, or descriptive keyword, call search_products FIRST, it is far cheaper than paging the whole catalogue (thousands of items). Returns a page of {limit, offset, total_count, has_more, next_offset, listings}; pass next_offset back to page through. Each listing has title, price in USDC (the exact wallet charge), listPrice (the price and currency on the brand store, when known), edition size, and remaining supply. Live on-chain minted count is in get_drop_details, not here. Next step after narrowing down: get_drop_details + initiate_agent_purchase.

  ConnectorNo auth

• goal-add-noteA

  Planner (proof-of-done)A

  Add a free-form note (markdown supported) to a goal — decisions taken, dead ends hit, context worth carrying into the next session. Notes are NOT evidence: they hang off the goal rather than an acceptance criterion and never count toward AC coverage or closing a Grove goal — use goal-attach-evidence for proof. Notes are visible in the goal detail panel and returned by goal-get under notes[].

  ConnectorNo auth

• list_climbing_routesA

  Spaghetti and Summits — First-Hand Dolomites AdventuresA

  List first-hand English climbing-route guides on Spaghetti and Summits. Returns each route's name and the URL of the guide on the blog. Call this when the user asks what climbing routes are on the site, or needs a link to a route page.

  ConnectorNo auth

• addA

  K-Work TrustA

  Adds two numbers and returns the sum.

  ConnectorNo auth

• addA

  agora402A

  Adds two numbers and returns the sum.

  ConnectorNo auth

• addA

  DomainCheckrA

  Adds two numbers and returns the sum.

  ConnectorNo auth

• addA

  casaA

  Adds two numbers and returns the sum.

  ConnectorNo auth

• addA

  solidusA

  Adds two numbers and returns the sum.

  ConnectorNo auth

• addA

  obolA

  Adds two numbers and returns the sum.

  ConnectorNo auth