"A local vector-based search engine for personal documents" matching MCP tools:

• get-space-documentA

  docuwriterA

  Use this when the user wants to read the full markdown content of a specific Space document/page after search or listing. Read-only: returns the selected document without changing content. Requires the document ID from list-space-documents, search-space-documents, or global-search.

  ConnectorOAuth

• 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

• build_knowledge_indexA

  agent4.ioA

  Build (or rebuild) the structured index for a knowledge base — the second leg beside vector search. Vector search answers "what does this passage say". It **cannot count, filter numerically or aggregate**, so "how many documents", "which ones are between 1000 and 2000 words", "how many per category" are not answered badly — they are structurally unanswerable. This builds a small per-KB table from whatever structured header the documents share, which the agent can then query with SQL via `query_knowledge_table`. Only worth it when the documents share a machine-readable header (a metadata table, YAML front matter, `Field: value` lines). **Prose gets declined, and that is the right answer** — a table of unique values makes statistics meaningless. `roles` names the fields that must be extracted **exactly** and never paraphrased. Use it when the answer has to quote something the model must not invent: - `identity` — what to call the item (book title, drug name, product name) - `link` — where to send the user - `image` — what to show the user - `code` — the unique identifier Which link is "the" link is a business fact the data does not state — only the customer knows. A declared role that cannot be found comes back in `roles.unresolved` **with candidate field names**: ask the user which one it is, do not guess. **Read `dropped` in the report and tell the user about it.** A column that was thrown out (coverage too low, two columns holding identical values) is invisible in later query results — the model simply works around it — so this report is the only place it is ever mentioned.

  ConnectorNo auth

• create_campaignA

  xmagnetA

  Create a DRAFT email campaign via a programmatic wizard. Call this tool and it will guide through the steps — no manual orchestration needed. WIZARD STEPS (handled automatically by the tool): 1. Call with contacts + total_contacts → tool returns engine picker (NextGen vs MyConvo) 2. Add campaign_type from user's click → tool returns campaign category chips (promotional, newsletter, event…) 3. Add campaign_category from user's click → tool returns engine-specific template gallery MyConvo: shows plain_email_templates (personal plain-text). NextGen: shows campaign_templates (HTML). 4. Add template_id from user's pick → tool creates the draft campaign. RULES: Reuse contacts from prior search — never re-search. Pass total_contacts from search result's total_in_crm so the user always sees the full count. Saves as DRAFT only — no emails sent.

  ConnectorNo auth

• verify_identityA

  Stipple — Document Verification & ExtractionA

  Run an Australian identity check over a SET of identity documents. A vision model reads each document (which ID it is, which fields it shows — name/photo/address/signature — and its issue date); a deterministic engine then tallies them against a scheme and reports whether identity is established, and exactly what's still missing if not. USE THIS WHEN someone needs to verify a person's identity from their documents — KYC / onboarding / "do these documents satisfy the 100-point check?" Pass ALL the person's documents together (a passport alone is 70 points; the check needs >= 100). `documents` is a list, each item ONE of: {"url": "https://..."} (public link, fetched server-side) or {"bytes_b64": "...", "filename": "passport.pdf"} (inline). Up to 10. `scheme`: "afp_100_point" (points, default) or "austrac_safe_harbour" (category combinations). Returns `{established, points/target or satisfied_path, documents[] (per-document: type, fields shown, whether it counted and why-not), reason, accepts, ...}`. This is identity COVERAGE, not a forgery judgment — run verify_document for authenticity. Documents are never stored.

  ConnectorNo auth

• find_agents_for_taskA

  AgentMarketplaceA

  Ranked candidate agents for a task, before any bid exists. Wraps AgentTrust's capability + trust search with local availability and budget-fit scoring (engine/matching.py, PLAN.md §7.1). Use ``evaluate_bids`` instead once actual bids have come in. Args: access_token: AgentAuth bearer token (requires ``market.read``). task_id: UUID of the task to find candidates for. limit: Maximum candidates to return, 1-50. Default 10. Returns: ``task_id``, ``matches`` (list of ``{agent_id, score, trust}``, ranked descending by ``score``), ``total``.

  ConnectorNo auth

• generate_policiesA

  lexvibeA

  Generate the legal documents (privacy policy, terms of service and, if applicable, an AI disclosure) localized and tailored to the target markets (GDPR, UK GDPR, CCPA…). Returns Markdown drafts. Pass check_website's or check_store's suggestedAnswers as `answers` so the documents disclose the right processing. Anonymous remote generation is template-based and capped at 3 locales; AI-tailored, hosted and auto-updated documents require a LexVibe account (https://golexvibe.com).

  ConnectorNo auth

• search_docsA

  pg-aiguideA

  Search documentation with hybrid semantic (vector) and keyword (BM25) search. Use semanticWeight to choose keyword-only (0), semantic-only (1), or a blend; mid values fuse rankings with RRF. Supports Tiger Cloud (TimescaleDB), PostgreSQL, and PostGIS.

  ConnectorNo auth

• get_university_detailsA

  Admit Coach — College Search & CostsA

  Read a college's admissions ranges, majors, costs and outcomes by IPEDS ID. Use search_universities to resolve a name first. Values are historical and may be missing; cite the returned school URL. No login, personal profile or student documents are accessed.

  ConnectorNo auth

• audit_citationsA

  Open Task RelayA

  Deduplicate supplied DOI, arXiv and URL citations before reviewing evidence. No authentication; deterministic comparison without storing inputs or fetching documents. Returns counts, normalized entries and duplicate groups with zero-based indices. Does not establish truth or source independence; use task_action verifications for a substantive review.

  ConnectorNo auth

• list_categoriesA

  ToolYour MCP ServerB

  List tool category families (Convertors, Documents, SEO Tools, etc.). Use before discover_tools to narrow search — e.g. discover_tools('pdf', category: 'Documents'). Free — not billed.

  ConnectorAPI key

• search_docsA

  Handsontable Docs MCP ServerA

  Semantic (meaning-based) search over the Handsontable + HyperFormula documentation knowledge base — docs guides, code recipes, blog posts, release notes and GitHub issues. Returns ranked page-level snippets with title, content, relevance score, url and provenance (framework, kind, htVersion/hfVersion). `url` is null when no public page exists (recipes, releases, issues) — never fabricate a link. Scores are rank-only. Guides repeat once per framework (javascript/react/angular/vue) — dedupe on url/title when you need distinct documents. Pass ht_version/hf_version (your installed releases) to get an explicit coverage note when the KB documents a different version.

  ConnectorNo auth

• add_document_to_collectionA

  DocImprintA

  Add an evidence bundle to a collection and trigger async vector indexing. Use after create_collection to populate a collection with documents. Once indexed, documents become searchable via search_collection and ask_collection. Indexing is async — poll get_job_status with the returned job_id until status is "complete". PREREQUISITE: Bundle must have status "complete" (check with get_bundle). Collection must be owned by your API key. Returns: { collection_id, bundle_id, job_id (poll for indexing completion) } Example prompts: - "Add my contract bundle ev_550e8400 to the Q4 Contracts collection." - "Put this evidence bundle into my Due Diligence Docs collection for search." - "Add document [bundle_id] to collection [col_id] with a title."

  ConnectorNo auth

• add_document_to_collectionA

  apiA

  Add an evidence bundle to a collection and trigger async vector indexing. Use after create_collection to populate a collection with documents. Once indexed, documents become searchable via search_collection and ask_collection. Indexing is async — poll get_job_status with the returned job_id until status is "complete". PREREQUISITE: Bundle must have status "complete" (check with get_bundle). Collection must be owned by your API key. Returns: { collection_id, bundle_id, job_id (poll for indexing completion) } Example prompts: - "Add my contract bundle ev_550e8400 to the Q4 Contracts collection." - "Put this evidence bundle into my Due Diligence Docs collection for search." - "Add document [bundle_id] to collection [col_id] with a title."

  ConnectorNo auth

• list_accountsA

  KeeploopB

  List the Apple Mail accounts this server is allowed to see, plus the configured scope. Call this first to learn which accounts exist before filtering a search by account. Each account carries its `categories`. Accounts are labelled (Personal, Work, ...). For a personal task use the Personal accounts; call list_categories if unsure.

  ConnectorOAuth

• search_shared_experienceA

  MAGNT MCP DoorA

  Search shared MAGNT memory for previously contributed task signals relevant to your current task. Provide only a minimal, non-sensitive description of the outcome you are currently trying to achieve. You may optionally describe the current blocker and approaches already tried. The shared memory is experimental and may contain no relevant match. A similar task is not evidence of a successful solution; learned observations, if present, are unverified. This search is read-only: your query is not added to shared memory or logs. Do not provide passwords, credentials, confidential documents, personal data, or details that are unnecessary for matching. Test records are excluded unless is_test is true.

  ConnectorNo auth

• contextual_adviceA

  Clara — Personal Clean Air PlannerA

  Personalised air quality advice for a UK location and a specific user context. Use this tool whenever the user asks an air-quality question that depends on *who they are* or *what they're about to do*: e.g. asthma, pregnancy, school-age child, gas cooker at home, tube commute, outdoor exercise. It composes location-specific pollution with the user's personal context to produce evidence-based advice — far more targeted than a generic "high pollution day" handout. Composable with Hermes: pass pm25/no2 from Hermes get_current_aq for advice based on live readings rather than annual average estimates. Returns structured advice with a plain-English summary, health context, and local intervention information. Present the 'summary' to users first. Args: postcode: UK postcode (e.g. "SE17 1RL"). Provides coords + LAEI pollution. latitude: Latitude for coordinate-based lookup. longitude: Longitude for coordinate-based lookup. pm25: PM2.5 concentration in ug/m3. Overrides location-based estimate. no2: NO2 concentration in ug/m3. Overrides location-based estimate. setting: Context — residential, school, workplace, outdoor_exercise, commute. has_gas_cooker: Whether the person has a gas cooker (affects indoor advice). commute_mode: If setting is commute — walk, cycle, bus, car, train, tube. has_indoor_sources: Indoor pollution sources (smoking, woodstove). audience: Target audience — general, children, elderly, respiratory, pregnant.

  ConnectorNo auth

• embedding_similarityA

  IA-QA — 130+ QA & Dev Tools for AI AgentsB

  Compute text similarity using local algorithms (Bag of Words, TF-IDF, Character N-grams). No API key needed — runs entirely in-process. NOT real embeddings: for true semantic similarity with vector embeddings, use run_semantic_tests with mode="embeddings" and your OpenAI API key. Supports single pair or batch mode with pipe-separated pairs. Useful for RAG retrieval testing, semantic search evaluation, and text deduplication.

  ConnectorNo auth

• normalize_vectorA

  IA-QA — 130+ QA & Dev Tools for AI AgentsB

  L2-normalize a float vector (produce a unit vector with norm=1). Required by many vector DBs (Pinecone, Qdrant cosine). Supports batch normalization of up to 1000 vectors.

  ConnectorNo auth

• vector_statsA

  IA-QA — 130+ QA & Dev Tools for AI AgentsB

  Compute statistics for a float vector or matrix of vectors: mean, std, L2 norm, min, max, sparsity, top-K indices. Useful for debugging embedding quality and analyzing vector distributions in a vector DB.

  ConnectorNo auth

• cortex_recallA

  mitosisA

  Semantic-only vector search over the memory, returning source excerpts. Prefer cortex_ask, which also uses full-text and graph expansion; reach for this when you specifically want nearest-neighbour matches on meaning.

  ConnectorNo auth