GitBook Model Context Protocol server - read and search GitBook documentation with AI assistants
GitBook Model Context Protocol server - read and search GitBook documentation with AI assistants. Exposed over MCP by the gitbook mcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
A Model Context Protocol (MCP) server that provides access to GitBook's API for AI assistants and LLM applications.
The GitBook MCP server enables programmatic access to GitBook Organizations, Spaces, Collections, and Content through a standardized MCP interface. It provides 12 tools for content operations and 6 AI-powered prompts for documentation workflows.
Everything the assistant can do here goes through one of these:
Prerequisites — The Prerequisites tool exposed by this serverTools — The GitBook MCP server provides 12 tools organized into functional categories. Each tool includes behavioral hints:Prompts — The GitBook MCP server provides 6 AI-powered prompts for documentation workflows:Development — The Development tool exposed by this serverDebugging — The Debugging tool exposed by this serverTesting — There are currently no unit or integration tests; running npm run test only checks that the TypeScript code compiles successfully (type-check/buildTroubleshooting — The Troubleshooting tool exposed by this servergitbook-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
You will need 3 environment variables: GITBOOK_API_TOKEN, GITBOOK_ORGANIZATION_ID, GITBOOK_SPACE_ID. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Gitbook MCP's toolset — Prerequisites, Tools, Prompts and 4 more — is a fair guide to whether it matches your workflow. It is maintained by rickysullivan; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Prerequisites | The Prerequisites tool exposed by this server. |
| Tools | The GitBook MCP server provides 12 tools organized into functional categories. Each tool includes behavioral hints: |
| Prompts | The GitBook MCP server provides 6 AI-powered prompts for documentation workflows: |
| Development | The Development tool exposed by this server. |
| Debugging | The Debugging tool exposed by this server. |
| Testing | There are currently no unit or integration tests; running npm run test only checks that the TypeScript code compiles successfully (type-check/build verification), and does not execute any actual tests. |
| Troubleshooting | The Troubleshooting tool exposed by this server. |
{
"mcpServers": {
"gitbook-mcp": {
"command": "npx",
"args": ["gitbook-mcp", "--organization-id=your_organization_id"],
"env": {
"GITBOOK_API_TOKEN": "gb_api_your_token_here"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| GITBOOK_API_TOKEN | Credential the server authenticates with. | Yes |
| GITBOOK_ORGANIZATION_ID | Configuration value read at startup. | Optional |
| GITBOOK_SPACE_ID | Configuration value read at startup. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.