"A search for a summary of a document" matching MCP tools:

• fluxink-mcp-chatgpt-create-layoutA

  fci-mcpA

  FluxInk document layout generator. Transform raw text content into a structured PDF using one of seven study or work templates, then preview it in an embedded PDF viewer widget. Supported layout_type values. cornell is the Cornell note taking layout with cue, notes, and summary. bullet_points is a clean bulleted summary. zettelkasten is atomic linked notes. journalism_5w1h is who, what, when, where, why, and how. meeting_add is a meeting agenda plus action items. sq3r is Survey, Question, Read, Recite, Review study notes. pso is Problem, Solution, Outcome. Use this when the user asks for a Cornell sheet, bulleted summary, Zettelkasten card, 5W1H breakdown, meeting agenda or minutes, SQ3R study sheet, or PSO writeup. Use this when the user wants to turn raw notes, lecture transcript, or source material into a printable PDF or formatted study sheet. Use this when the user asks for a downloadable PDF document of their content. Do NOT use this when the user just asks for a plain summary in chat. Give it inline. Do NOT use this when the user wants to handwrite or draw something. Call show_handwriting_canvas instead. Do NOT use this when the user wants text in a personal handwriting style. Call show_style_canvas instead. Do NOT use this for plain informational requests with no document generation intent. Always pass the source material verbatim in the content parameter. Do NOT pre summarize. The layout engine handles structuring. Pick the layout_type that best matches the stated purpose. If unclear, ask one short clarifying question instead of guessing. Do NOT re-call if a layout PDF is already visible from a previous turn unless the user explicitly asks for a different layout, different content, or a regeneration. After calling, write a single short acknowledgement and do NOT restate the PDF content.

  ConnectorNo auth

• get_filingA

  HKEx FilingsA

  Download one HKEx document by its URL and read, page through, or search its text. ``link`` must be an HKEx document URL from search_filings (host ``www1.hkexnews.hk``); any other host is rejected. With ``extract=True`` (default) the response includes up to 30 ``tables`` and a window of extracted ``document_text``: ``max_chars`` characters starting at ``offset``. Long reports return ``next_offset``; call again with it to read the next window. Pass ``query`` to search the whole document instead: the response then lists up to 20 case-insensitive matches with their offsets and surrounding text, plus ``match_count`` — use a match offset to read that part. Set ``extract=False`` for size and content type only.

  ConnectorNo auth

• fetchA

  OneQAZ Trading IntelligenceA

  Purpose: ChatGPT-connector-standard document fetch by id from `search` results. Namespaces: `tool:{name}` returns the tool's full documentation and how to call it; `resource:{uri}` returns the resource's live data (core resources resolved server-side — also the bridge for clients without MCP resource support, e.g. Gemini); `signal:{market}:{symbol}` returns the symbol's latest combined signal. Triggers: ChatGPT connectors / Deep Research call this after `search`. Clients without MCP resource support can call it directly with a known resource id, e.g. fetch("resource:market://global/summary"). When to call: whenever the full content behind a search result id is needed. Prerequisites: a valid id — from `search` results or a known namespace id. Next steps: for tool docs, call the named tool via tools/call; for signals, get_signal_detail / explain_decision for deeper evidence. Caveats: uncovered resource uris return description-only text (no fabricated data). `text` is a JSON document for resource/signal ids. Output: {id, title, text, url, metadata, disclaimer, is_investment_advice, data_classification} — flat envelope, OpenAI fixed shape. Output nature: Observed signal state computed from live market prices each cycle. signal_score is an internal ranking score, not a probability; bias is its sign. Context for the user's question, not investment advice.

  ConnectorNo auth

• fetchA

  MaplithA

  Read one map document by the id a search result handed you. Ids: object:<name>, finding:<id> or finding:<finding_key> (stable across rescans), process:<object type>, metric:<name>, statement:<id> (run-scoped: search again after a rescan), playbook:<id>. It is the second half of the search/fetch pair that connector clients such as ChatGPT require, and returns id, title, text, url and metadata with the direct tools' data flattened to text. If your client can call the direct tools, use them instead (structured, no search first): get_object for an object you can name, get_process for a process, get_metric for a metric, list_findings for findings by status. Use fetch for a result search handed you, or a finding_key.

  ConnectorOAuth

• get_documentA

  RegAlert - fintech and crypto compliance and regulatory documentsA

  Read one document: metadata, summary, lineage and the English text (markdown). With `query`: only the passages that hold those words — the cheap way into a long document. Without: the text from `offset`, 40000 characters a call. Free under fair use: at bulk scale full-text reads pause until the next day (UTC); search and lineage keep working. For bulk access write to ask@regalert.today.

  ConnectorOAuth

• cern_inspire_get_citation_summaryA

  cern-inspire-mcp-serverA

  Compute INSPIRE-HEP's citation summary for one author or for any literature query: h-index, citation totals, average citations per paper, and paper counts per citation bucket (0, 1–9, 10–49, 50–99, 100–249, 250–499, 500+), each for all citeable papers and for published papers, plus citations received per year. Pass exactly one of author (a BAI, ORCID, INSPIRE ID, or author recid — resolve a name with cern_inspire_search_authors first) or query (any INSPIRE literature query: a topic, collaboration, institution, or "a <BAI>"). Document type and subject filters narrow every figure. year_from and year_to narrow the summary to papers from those years, and exclude_self_citations recounts it without self-citations; any of them leaves out citations per year, which INSPIRE cannot narrow that way.

  ConnectorNo auth

• search_my_document_contentsA

  X1 WealthA

  Search the text (body contents) of the connected person's own documents in X1, such as trusts, policies, agreements, and K-1s, when they ask what their own documents say. Returns the matching passages with document and page, sheet, or section so you can answer from them and cite the page; it does not write the answer itself. To search by document name, title, or tag instead, use the document metadata search if one is offered. To compare known files, pass up to 10 authorized documentIds in one request instead of parallel per-file calls. all_requested coverage requires a matching passage from every selected document; best_effort can return partial evidence. Neither is a complete page-by-page review. If rate-limited, wait for outstanding searches and retry one at a time. Indexing is asynchronous after every save; a just-saved document may return an honest still-indexing state with an instruction to try again shortly. Governed retrieval contract: x1-vault-v1.

  ConnectorAPI key

• fetchA

  Cubite LMS: Learning Management SystemA

  Read one result found via `search` as plain text with its public page URL, for quoting or citing it in an answer; this is the fetch half of the search/fetch pair. Pass the result's id exactly as search returned it (e.g. "course:..."). Returns {id, title, text, url, metadata}. A course's text is its public catalog summary (name, description, level, duration in hours, price, subjects, topics), not its lessons. A missing document, another site's content, and a type this connection cannot read all return the same not-found error; an id without a type prefix is rejected as invalid. To work with a course rather than quote it, use course_get for its settings record (ids, flags, dates, enrollment count) and course_content_get for its lessons as EditorJS blocks.

  ConnectorAPI key

• kb_get_documentA

  MangroveAIB

  Read a requested KB guide or a known source section by slug. Use directly when the user requests the document itself; no preliminary graph call is required. For a general explanation use query_knowledge op=ask, not a document-reading sequence. If a needed slug is unknown, locate it with kb_search or kb_list_documents. Use view=overview for a guide summary; view=section with a returned section_anchor for a specific passage. Content defaults to 6000 characters; offset and next_offset count characters within the selected body. Continue only when the requested material is missing, not merely because has_more is true. full=True is for explicit full-document requests. A document excerpt is educational material; executable signal identities and parameters come from the runtime registry.

  ConnectorNo auth

• create_documentA

  ProductNowA

  Create a NEW ProductNow document and generate its content with AI. Use this to persist knowledge the user wants remembered or shared across sessions and teammates — decisions, specs, RFCs, plans, meeting outcomes. Search with search first so you don't duplicate an existing document; to change an existing document use edit_document instead. File the document in an existing folder. Search results include each document's folderId; pass the folderId of the closest related document. If search does not show a fit, fetch_folder the root and walk folders until you have a folderId. Leave folderId off only when the user explicitly asked for the warehouse root. If no folder fits, call create_folder under the closest existing folder and pass that new folderId. Content is generated from `prompt` (the full outline: numbered sections, their titles, and what each should say) and `context` (verbatim source material the user supplied or explicitly authorized for this ProductNow document). Generation paraphrases: if exact wording must survive, put it in `context` and say so in `prompt`. Pass `templateId` only when you already have one. Returns the documentId and URL; generation continues after the call returns.

  ConnectorAPI key

• rememberA

  ProductNowA

  Store one piece of information in ProductNow when the user says 'remember this', 'save this', or 'note that…' about their company, product, customers, or team. Pass the fact as `content`; ProductNow decides where it belongs — it searches the warehouse, edits the existing document that covers the topic, or creates a new one in the right folder. ProductNow handles search, folder selection, and document choice within the background job, so separate search, fetch, or placement is not needed. Returns success immediately; a success response means the job was queued and processing continues in the background. Polling is not supported. Use edit_document or create_document instead only when the user already named the exact document or outlined a whole new document.

  Connector

  Destructive

  API key

• SearchDocumentA

  EquiblesA

  Search one SEC filing or earnings-call transcript by document ID. semantic mode uses hybrid relevance and returns excerpts in document order with approximate line numbers. exact mode performs a literal case-insensitive substring match and returns precise matching lines. Get document IDs from SearchDocuments or ListFilings; use ReadDocumentLines for surrounding text.

  ConnectorNo auth

• mcpParseA

  AILANG ParseA

  Parse a document into structured blocks, Markdown, HTML or A2UI, or a short summary of it. Give the document ONE way: fileRef: an uploaded file (mcp-file://docparse/file_...). The same user can use it again for 30 minutes after the first use (more parts, another format), then it is deleted. file: in ChatGPT, the file the user attached (ChatGPT fills it in). filepath: an https:// URL of a publicly reachable document, or a sample id from mcpFormats such as "sample_docx_formatting". content + filename: short text only (Markdown, HTML, CSV); the filename's extension picks the parser. outputFormat: blocks (default), markdown, html, a2ui, or summary (counts, the first 50 headings, warnings: a few KB). Look with summary first when a document may be large. Large documents come in parts: when the result has page.nextCursor, call mcpParse again with the same fileRef/filepath and cursor=<nextCursor> for the next part; read every part before answering about the whole document. maxChars sets the part size as a string of digits (default "80000", "2000".."120000"). Which way to send a file: a file in your sandbox or workspace: call createUpload (one token PER FILE; set count for several) and run its curl line, then call this tool with the fileRef the upload prints. curl fails with a network error, or the user wants to pick a file: call uploadDocument; the user chooses it in the AILANG Parse card, which uploads it and gives you its fileRef. a public https:// link: filepath. Short text: content. Never parse the file yourself (your own script, or your own reading of it) and present that as this tool's result: if the file cannot be sent, tell the user.

  ConnectorNo auth

• search_contentA

  Anahana Content MCPA

  Search Anahana's wellness content — angel numbers, astrology, zodiac, tarot, crystals, yoga, meditation, breathing exercises, mental and physical health, and more — in any of 24 languages. Returns matching articles with title, url, section, language, and a short summary. Matching is KEYWORD/SUBSTRING over title, description, section and slug; it is NOT semantic search, in any language. For zh, ja and th the query is not word-segmented, so it is matched as one substring. The index is regenerated on every site deploy; exact live per-language document counts are in each response's _meta and at https://www.anahana.com/content-index/manifest.json.

  ConnectorNo auth

• fetchA

  FirmTape - SPX, ES, NQ, RTY gamma levels, 100+ symbolsA

  Retrieve the full text of one FirmTape document by the id `search` returned: `session:YYYY-MM-DD` for a finished trading session, `page:/path` for an explainer or research page. A FirmTape URL or a bare YYYY-MM-DD trading day is accepted too. Use when: you hold an id from `search`, or a client that only speaks search/fetch (ChatGPT). Not for: structured numbers — get_session and get_levels answer the same day with fields instead of prose. Limits: public FirmTape documents only; long pages are truncated with a link to the rest.

  ConnectorNo auth

• revoke_documentA

  Formify — AI Assisted E-SigningA

  Revoke a document that has been sent for signing (only possible if not yet fully signed). Always call get_document first to confirm status, then show the user a summary and ask for confirmation — revoking is irreversible.

  Connector

  Destructive

  OAuth

• analyze-documentA

  GigSoul x402A

  Evaluate a document or article and say what to do about it: a short summary plus key insights, weaknesses or gaps, and concrete recommendations. Use when you need judgment or next steps. For a neutral digest only, use summarize-document (cheaper). For customer complaints inside a text, use extract-pain-points. URLs are not fetched; paste the text. Pay-per-call: $0.05 USDC on Base via x402. Without a payment-signature header the call returns an error whose data carries the payment terms.

  ConnectorNo auth

• search_documentsA

  RegAlert - fintech and crypto compliance and regulatory documentsA

  Full-text search over the documents. Free. Each hit: uid, title, date, regulator and the first 300 characters of its summary — never the text (get_document). `total` is exact. Filters `licence` and `in_force_only` use the index when it carries the facts; if not, the hits are filtered after the search (`total` then counts those hits) or, with no facts on the hits, the filter is not applied. The answer carries a `note` in both cases. `fields` can add in_force_status (in_force = no newer amending or superseding document is known to RegAlert; not a checked commencement date), applies_scope, applies_licences, effective_date.

  ConnectorOAuth

• get_library_documentA

  DistillaA

  Read one Public Library document by document_id from search_public_library sources. Returns metadata, summary, and tags. Pass with_contents=true to include raw text in contents for non-Research documents. Research documents omit full text (provider terms) and set contents_omitted. Omit with_contents to keep the payload small. This tool does not search. Call search_public_library first.

  ConnectorOAuth

• summarize_artifactA

  XenitionA

  Use this when the user wants a summary of one of their Xenition documents, notes or research — a TL;DR, key points, action items or a fuller summary. Works on long documents in full. Do not use to change the document (use edit_artifact).

  ConnectorNo auth

• wenmar_bulletinsA

  Wenmar OpenA

  Manufacturer communications NHTSA publishes: service bulletins, service campaigns, warranty extensions and over-the-air updates. Each has NHTSA's summary, the manufacturer's own document number, and `document`, the address NHTSA's copy of the document is expected at (not confirmed; null for old ones). The document itself is the manufacturer's and is not returned. A bulletin lists model years: it is not a recall and does not say a vehicle is affected. action=vehicle takes `id`, a vehicle id such as "2018_ford_f-150", and gives one page of that model year's bulletins, newest first, with `counts` by type, component, trouble code and topic. action=vin takes `vin` (and optionally `year`) and does the same for the model year the VIN decodes to. action=get takes `nhtsa_id` and gives one bulletin with every vehicle it lists. action=search lists all bulletins newest first, narrowed by `make`, `model` (needs `make`) and `year`. Every action but get takes `type` (service_bulletin, service_campaign, warranty_extension, over_the_air, emissions, other), `component` (an id from `counts.components`, such as brakes), `code` (a trouble code such as P0420), `topic` (maintenance), `query` (free text in the summary, such as a symptom), `limit` (at most 100, 25 when left out) and `cursor` (`next_cursor` of the page before). This tool needs the hosted service: a local data file does not hold bulletins.

  ConnectorNo auth