GitBook MCP server
Create sites and spaces, open and review change requests, and read or edit GitBook content.
- “Create a new GitBook documentation site”
- “Open a change request against our docs”
- “Update a page in our GitBook space”
GitBook serves an AI Catalog
manifest at /.well-known/ai-catalog.json on gitbook.com, declaring
5 agentic resources
that a discovery service can index without asking anyone’s permission.
/.well-known/ai-catalog.json. ARD v0.91 renamed the path to /.well-known/ard.json and made the old one an optional courtesy, so a consumer implementing only the current spec will not find this manifest.
specVersion in the manifest. 1.0 is current for the AI Catalog data model; anything lower is an earlier draft. ARD reads this field as transport-defined and ignores it.host-no-identifiercontent-type-not-ai-catalog-jsoncors-not-readable-cross-originCreate sites and spaces, open and review change requests, and read or edit GitBook content.
Product documentation index in LLM-readable form, with a Markdown version of every page.
Reference documentation for the GitBook REST API: organizations, sites, spaces, content, change requests and analytics.
Skill documents that teach coding agents how to author GitBook content and configure sites.
Machine-readable catalog of GitBook's public APIs, with links to reference documentation and status.
Content-Type: application/json —
yesAccess-Control-Allow-Origin: * —
no — header absenthttps://gitbook.com/.well-known/ai-catalog.json on 2026-09-13, HTTP
200. The verbatim body is stored alongside its manifest in the
GitBook repository
as ai-catalog/gitbook-ai-catalog.json. Nothing on this page is derived
or generated: an AI Catalog manifest is served from the publisher’s own domain or it does not
exist, which makes it — like an
A2A Agent Card — one of the few agent artifacts that cannot be
produced on a provider’s behalf. Grades are recomputed on every build; the specification is a
v0.9 draft and
these verdicts will move when it does.
Every descriptor here is available over the APIs.io API and to AI agents over MCP. Agent Discovery is not yet its own endpoint on the v1 API. Reach it through catalog search and the tag graph, or the MCP server.