MCP tool reference · #85 of 563 by publishers
get_doc
Exposed by 23 servers from 22 publishers, read from the live servers by the Serverdex check; most of them sit in Documents & Knowledge; 34.8% of them take a path parameter; the most-starred is Proa documentation (396 stars).
get_doc(path: string, slug: string, …)Parameters
share = % of the 23 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| path | string | 34.8% | 100% | A docs path from search_docs or list_docs, e.g. "/docs/agreements/ndas" or "/pricing". A full undocsend.com URL or a .md URL also works. |
| slug | string | 26.1% | 66.7% | One of: overview, rest-api, mcp, cli, versioning, llms, auth. |
| id | string | 17.4% | 100% | Doc id. |
| url | string | 13% | 66.7% | A docs.metamask.io URL, e.g. https://docs.metamask.io/embedded-wallets/sdk/react/ |
| offset | integer | 8.7% | 0% | Character offset to start reading from. |
| doc_id | string | 4.3% | 100% | — |
| docs_ref | string | 4.3% | 0% | Docs channel or immutable ref. Defaults to stable. |
| engine_version | string | 4.3% | 0% | Optional Tandem engine version hint for compatibility checks. |
| exec | string | 4.3% | 0% | Opaque exec token from warning-copy link (?exec=). Optional if already embedded in id. |
| format | string | 4.3% | 0% | Which serialization to return. Default `markdown`. Use `content` to round-trip TipTap JSON back into update_doc for structural edits. Use `all` for the legacy t |
| heading | string | 4.3% | 0% | Optional. Return only the section under this heading (exact heading text): the heading through the next heading of the same or higher level, the same range upda |
| heading_occurrence | integer | 4.3% | 0% | Optional, with `heading`. When the heading appears more than once, which one to read, counting from the top: 1 is the first. Same numbering as update_doc_sectio |
Source: the input schema each server returns for get_doc, aggregated over the 23 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with get_doc
23 of 23 · 22 publishers · 23 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes get_doc |
|---|---|---|---|---|---|---|
| 1 | Proa documentationproa-labs · Documents & Knowledge | proa-labs | Documents & Knowledge | 396 | yes | Read a complete official Proa documentation page as Markdown with its title, description, and canonical route. Supply a path returned by search_docs or resources/list. Only published documentation is accessible; arbitrary URLs and filesystem paths are not fetched. |
| 2 | Docs MCPfrumu-ai · APIs & Integrations | frumu-ai | APIs & Integrations | 126 | yes | Fetch and normalize a published Tandem docs page by path or URL. |
| 3 | Wrapswraps-team · Documents & Knowledge | wraps-team | Documents & Knowledge | 69 | yes | Return the full markdown source of one Wraps page. Call list_docs first to see which paths have markdown. |
| 4 | StitchAPI Docsrejifald · Documents & Knowledge | rejifald | Documents & Knowledge | 21 | yes | Fetch a full StitchAPI documentation page as Markdown — the "read the whole thing" escape hatch for a search_docs hit. Pass a `url` (as returned by search_docs) or a `slug` like "guides/resilience/throttle". |
| 5 | Pine Script v6 Documentationpaulieb89 · Developer Tools | paulieb89 | Developer Tools | 11 | yes | USE WHEN reading the full content of a Pine Script v6 documentation file. Returns the file content; when limit is set, a header shows the char range and offset to continue reading. AFTER calling this tool, use offset=<end> to continue if the header indicates more content is available. For large files (ta.md, strategy.md, collections.md, drawing.md, general.md), prefer list_sections() + get_section |
| 6 | amCharts 5amcharts · Developer Tools | amcharts | Developer Tools | 9 | yes | Get a full documentation page — an extended doc by path, or a skill file by 'skill/<name>'. Paths are the source labels that search_docs and search_all print. |
| 7 | MetaMask Embedded Wallets (Web3Auth) MCPweb3auth · Crypto & Web3 | web3auth | Crypto & Web3 | 5 | yes | Fetch the full content of a MetaMask Embedded Wallets documentation page by URL. Sources: Algolia, llms.txt, GitHub MDX. |
| 8 | AGILEX Docswgjsg · IoT & Devices | wgjsg | IoT & Devices | 1 | yes | Read one documentation page as Markdown. Call this with a ``doc_id`` returned by ``search_docs`` (or a slug such as ``ymZimX7JLe``). Manuals are often 20k-60k characters, so this tool paginates: if the reply has ``truncated: true`` and a ``next_offset``, call again with that ``offset`` to continue. Do not re-request the same offset. Args: |
| 9 | SWATGenXswatgenx · Other | swatgenx | Other | 1 | yes | Return one full SWATGenX documentation chapter as markdown, by chapter slug; 'overview' is the index and lists every chapter. Retired slugs are followed to their current chapter automatically. |
| 10 | ToGOtogo-framework · Developer Tools | togo-framework | Developer Tools | 1 | yes | Fetch a repo's full README/documentation as Markdown. |
| 11 | SanctionsKit developer MCPsanctionskit · Developer Tools | sanctionskit | Developer Tools | 1 | yes | Read a document returned by search_docs, including code examples and error handling. Uses a fixed local document catalog; does not fetch arbitrary URLs. |
| 12 | @imqueueimqueue · Developer Tools | imqueue | Developer Tools | 1 | yes | Fetch the markdown of an @imqueue documentation page by its URL (as returned by search_docs). Returns plain markdown suitable for reading and quoting. Pass a URL with a #fragment — which is what search_docs returns for a section result — to get just that section plus the heading path above it; pass the URL without one to read the whole page. Only imqueue.org (framework docs) and imqueue.com (licen |
| 13 | undocsend docsitseasyco · Documents & Knowledge | itseasyco | Documents & Knowledge | — | yes | Return one undocsend docs page (or /features, /pricing, /security) as markdown. The path must be one returned by search_docs or list_docs. |
| 14 | NEARpediaunitynodes · Documents & Knowledge | unitynodes | Documents & Knowledge | — | yes | Read the FULL text of one indexed NEAR documentation page by id (NEAR node and developer docs plus partner docs) — exact commands, flags, and whole sections a search snippet truncates. Best for NEAR operational/how-to questions. NEAR docs only, not the docs of other projects or the web. Get the id from search or semantic_search first. |
| 15 | Harshith Nayaka L portfolio docsharshithnayakal · Finance | harshithnayakal | Finance | — | yes | One developer document in full, as markdown (the OpenAPI description is YAML). |
| 16 | UmbHost Knowledgebaseumbhost · Search & Web | umbhost | Search & Web | — | yes | Fetch one documentation page as full markdown by its path (as returned by search_docs or list_docs). |
| 17 | lovefengis docssystemonster · Documents & Knowledge | systemonster | Documents & Knowledge | — | yes | Get the full Markdown of one documentation page by slug. Slugs come from search_docs. |
| 18 | Canton Ccpediaunitynodes · Crypto & Web3 | unitynodes | Crypto & Web3 | — | yes | Fetch the FULL text of one indexed Canton-ecosystem documentation page (Canton/Daml/Splice and integrated partner docs) by its numeric id. Canton-specific. Use this AFTER search or semantic_search returns a doc id, to read complete commands, flags, and full sections a search snippet truncates. Requires an id. Not a discovery tool; use search/semantic_search first. |
| 19 | Docktry-dock-ai · Media & Creative | try-dock-ai | Media & Creative | — | yes | Read a workspace's doc (TipTap rich-text) body. Format is negotiable via `format`: `markdown` (default — CommonMark + GFM, ready to feed to an LLM or render in a non-ProseMirror surface), `content` (TipTap JSON, round-trippable into update_doc for structural edits), `text` (plain text, best for search, summarisation, word-count heuristics), or `all` for the legacy three-in-one shape. Default is `m |
| 20 | SilvaLabsio.github.opensylva · Documents & Knowledge | io.github.opensylva | Documents & Knowledge | — | yes | Read one document: metadata + compact brief/TOC by default to save context. Do NOT use view='full' unless you specifically need the complete raw text or code. Prefer reading specific sections via get_doc_section using the chunk_index or heading from toc. Default view (omit or head): cascade brief — ai_md → summary → short clean_md (≤12KB) → else body null + toc/hint. Other views: brief | summary | |
| 21 | Splice docsrogues-lab · Documents & Knowledge | rogues-lab | Documents & Knowledge | — | yes | One agent doc as markdown: getting-started, authentication, mcp or pricing (pricing includes the live model table). |
| 22 | lucid.pagebitgate · Content & Publishing | bitgate | Content & Publishing | — | yes | Fetch the canonical Markdown source of a page. Public and unlisted pages are open to anyone; private pages require the owner's lp_ API key. |
| 23 | RideDesk Developer Docsridedeskapp · Developer Tools | ridedeskapp | Developer Tools | — | yes | One documentation topic as markdown: the booking API contract, checkout, widgets, attribution, live chat, the customer portal, or the per-account booking MCP server. |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.