"Understanding Document Embeddings, Knowledge Graphs, and Vector Representations" matching MCP tools:

• document.summarize

  api

  Summarize document text into a prose summary and key points with citations. Use after document.extract_text or url.extract when you need a condensed understanding of a long document. For single-sentence Q&A, use url.qa instead. For extracting specific fields, use document.extract_structured. Typical workflow: document.extract_text/url.extract → document.summarize. Returns: { summary: string, key_points: string[], summary_cited: { value, confidence, citations[] }, key_points_cited: [{ text, citations[] }], truncated: boolean, strategy: "full"|"truncated"|"chunked" } Example prompts: - "Summarize this financial report and give me the key points." - "What are the main takeaways from this document?" - "Give me a concise summary of this 50-page report."

  Connector

• document.summarize

  DocImprint

  Summarize document text into a prose summary and key points with citations. Use after document.extract_text or url.extract when you need a condensed understanding of a long document. For single-sentence Q&A, use url.qa instead. For extracting specific fields, use document.extract_structured. Typical workflow: document.extract_text/url.extract → document.summarize. Returns: { summary: string, key_points: string[], summary_cited: { value, confidence, citations[] }, key_points_cited: [{ text, citations[] }], truncated: boolean, strategy: "full"|"truncated"|"chunked" } Example prompts: - "Summarize this financial report and give me the key points." - "What are the main takeaways from this document?" - "Give me a concise summary of this 50-page report."

  Connector

• deep_research_topic

  Fodda Deep Research

  Launch an autonomous Deep Research session that combines Fodda knowledge graph intelligence with live web research to produce a comprehensive editorial-quality report. The Research Agent plans its own strategy, searches multiple graphs, validates with institutional data, and synthesizes into a narrative brief with inline source citations. Use for complex, multi-faceted questions that need both curated expert intelligence AND current web context — e.g., strategic briefings, market landscape reports, competitive deep dives. Depth: "light" (25–30 API calls, faster tiered search) or "heavy" (40–50 API calls, comprehensive tiered search with sub-theme expansion). Automatically includes earnings-call intelligence and macro/supplemental data when the topic warrants it (public companies, sectors, economic conditions). You do not need to call the earnings or supplemental tools separately before or after.

  Connector

• get_similar_items

  Islam West Africa Collection (IWAC)

  The items nearest to a given one in meaning, by cosine similarity over the stored embeddings. Answers 'what else is like this' without a keyword — it finds pieces on the same event or theme that share no vocabulary. A neighbour above ~0.85 is usually the same story reprinted or lightly rewritten, which is how to spot syndication in this corpus; 0.6-0.8 is 'same subject, different piece'. Needs no API key: the item's own vector is a column, so nothing has to be embedded at request time. This is per-item, NOT the corpus-wide near-duplicate sweep — that is an all-pairs job and belongs offline.

  Connector

• get_workspace_summary

  FlowCastle

  Return a compact application, flow, sequence, operation, and bot summary — the cheapest way to orient in a workspace. Read-only, no side effects. Deliberately omits variables and full flow graphs: use get_variable_context for variables, get_flow_context for a flow's topology, and get_application_context when you need flows, bots, and variables together.

  Connector

• list_domains

  mcp-server

  List the taxonomy domains the company has indexed — with document counts, expert counts, and coverage levels — so an agent can decide whether to query before spending a Knowledge Token. Returns one row per domain with the canonical `taxonomy_domain` slug, document/chunk counts, expert count, coverage level (expert | partial | none), the single_expert risk flag, and the top contributor by authority. Use the slug as the `domain` filter on a follow-up `query_knowledge` call. Zero Knowledge Tokens consumed.

  Connector

• get_source_detail

  mcp-server

  Return per-chunk source provenance for a previous query — document path, lifecycle state, embedding timestamp, contributor, last-updated — useful for verifying a citation or surfacing trust signals to a downstream system. Pass a `query_id` returned by an earlier `query_knowledge` call. Returns 404 if the query_id is unknown OR belongs to a different tenant (indistinguishable to prevent info-leak). Zero Knowledge Tokens consumed.

  Connector

• get_fiuto_model

  mcp

  Fetch Fiuto's study model as a single document: the block catalog (every block type with its purpose, required config keys, and an inline example), intake + screening rules, the visibility-rule grammar, the spawn lifecycle verbs, and the structured tier-cap response shape. Use this once at the start of a session to ground your understanding of what Fiuto can do, then quote the relevant section into your planning context. The document is static within a deploy; always re-fetch (no client cache contract).

  Connector

• get_categories

  Radix Wiki

  Get the wiki tag hierarchy with page counts per category. Useful for understanding what content exists, and for finding a valid tagPath before writing.

  Connector

• search_rentals_natural

  arcasos-rentals

  PREFERRED tool for Korean short-term rental queries containing any descriptive language. ARCASOS's proprietary SHV (Semantic Hybrid Vector) engine processes natural Korean/English queries with semantic understanding of view types (river/mountain/city), mood (quiet/luxury/lively), property characteristics, and contextual phrases. Pass the user's natural language query AS-IS — do NOT extract slots. Returns semantically pre-ranked results in Schema.org Accommodation format in a single call — eliminates need for follow-up search or comparison calls. Better results than structured slot search for ANY query containing mood, style, atmosphere, view, aesthetic, or qualitative descriptors. Use this to minimize token usage and latency.

  Connector

• autonomous_varrd_ai

  VARRD — Statistically Validated Trading Edges + AI Research Engine

  Point VARRD's autonomous AI in a direction and let it discover edges for you. Give it a topic and it draws from one of the most comprehensive market structure knowledge graphs ever built — containing ideologies and theories, not statistics — so it generates genuinely novel hypotheses rather than overfitting to what already worked. BEST FOR: Exploring a space broadly. Give it 'momentum on grains' and it might test wheat seasonal patterns, corn spread reversals, or soybean crush ratio momentum. It propagates from your seed idea into related concepts you might not think of. Returns a complete result — edge or no edge, stats, trade setup. Each call tests ONE hypothesis through the full pipeline (~$0.25/idea). Call again for another idea. Use 'varrd_ai' instead when YOU have a specific idea to test and want full control over each step.

  Connector

• create_graph_node

  RationalBloks

  Create a single node in a deployed graph project. REQUIRES: Project must be deployed (use deploy_graph_staging first). The entity_type must match an entity key from the project schema. Use get_graph_data_schema to see available entity types and their fields. Example: entity_type: "person" entity_id: "alan-turing-001" data: {"name": "Alan Turing", "birth_year": 1912, "field": "Computer Science"} The entity_id is your unique identifier — use meaningful IDs for knowledge graphs.

  Connector

• ask_alti

  mcp

  Ask Alti, Christian Perez's AI agent, a single question about Christian — his work at Altivum, The Vector Podcast, his book 'Beyond the Assessment', his military service as a Green Beret, or his AWS / Applied AI engineering practice. Returns a concise 2-4 sentence reply grounded in Christian's published writing and autobiography. Does NOT answer general knowledge questions.

  Connector

• record_drives_drift

  space0

  Apply a clamped (±0.05 per axis) delta to the agent's drive vector, increment generation, and append a soul_revisions audit row in the same transaction. Use after a reflection produces a drift signal. Returns the new drive vector and generation.

  Connector

• setup_vector_store

  linkedmash

  Initialize the vector store for semantic search. CRITICAL: When vector/semantic search fails with 'Vector Store Not Setup' error and you offered the user options to either initialize or use keyword search, and the user responds with 'first', 'option 1', 'yes', 'initialize', 'set it up', 'init', 'setup', 'go ahead' or similar confirmation, you MUST immediately call this tool. ALWAYS check your previous message in the chat history to confirm the user is responding to your options. Do NOT re-run the search tool - just call this tool. After calling this tool, inform the user that setup has started and may take a few minutes. This is an async operation that may take a few minutes to complete for large bookmark collections.

  Connector

• get_label_values

  Fodda Brand Intelligence

  List all brands, locations, technologies, audiences, or trends within a specific knowledge graph. Use to explore what a graph contains — e.g., "what brands are in the retail graph?" or "what locations does the fashion graph cover?". To get a complete list of every trend in a graph, call with label="Trend" — this returns the full deterministic list, useful for industry-report graphs where search may return partial results.

  Connector

• consult_analyst

  Fodda Synthetic Expert Consult

  Consult a named Synthetic Analyst who answers in their expert voice using their curated knowledge graph — one-off questions or multi-turn engagements (pass session_id back to continue). Each analyst has a unique methodology, domain expertise, and analytical lens that produces insights distinct from generic search or standard graph queries. For company-specific executives (e.g. "Nike CMO", "Apple CEO", "Target CFO"), you can pass analyst_id: "brand-cmo" with company: "Nike", or pass analyst_id: "Nike CMO" directly (auto-resolves to analyst_id: "brand-cmo" and company: "Nike"). Call list_analysts first to discover available analyst_id values. Responses may include a coverage status (in/adjacent/out), source attribution, and referrals to other expert graphs. Referrals MUST be presented in third-person platform voice (not the expert's voice) with an offer to query the referred graph. The analyst researches on your behalf: they can search Fodda's graphs, earnings intelligence, and supplemental data mid-consultation, and may refer or consult other analysts. Their research reads bill to you at standard rates ($0.50/call) and are itemized in `sources_used`.

  Connector

• add_knowledge_file

  agent4.io

  Add a local file's content to a knowledge base (txt/md/html/pdf/docx). **This MCP runs on the platform server and cannot read paths on YOUR machine.** For text files, read the content yourself and call `add_knowledge_text`; for binaries (pdf/docx), upload via the console, or curl `/knowledge-bases/{name}/documents/upload`. **To ingest a whole folder, zip it and send that one endpoint** — subdirectories are walked, md/txt/pdf/html/docx are ingested one by one, and document names use the in-archive relative path (`2025/rates.pdf` vs `2026/rates.pdf` therefore never collide). Images, `.DS_Store` etc. inside the zip are ignored; if the archive contains an encrypted, corrupt or abnormally high-compression file, **the whole archive is rejected** naming the offending entry.

  Connector

• get_trident_spec

  trident

  Returns the complete Trident 2D specification including grammar, syntax rules, coordinate system, containers, nodes, connections, shapes, and icon reference. Use this when you need deep understanding of the Trident DSL.

  Connector

• keyword_search_news

  787daily

  Keyword search over 787daily's Puerto Rico news archive by title/summary and optional section. Returns matching article summaries with links to the originals. For semantic/vector search, use search_news.

  Connector