GitBook

You can connect to GitBook content and workflows through a dedicated MCP server that exposes content, spaces, collections, and AI-assisted prompts. This server lets you discover, read, search, and retrieve documentation data programmatically while supporting automation and AI-driven documentation tasks.

How to use

To use the GitBook MCP server, configure an MCP client to connect via the provided stdio or http options. You can run multiple client configurations to integrate with IDEs or AI assistants. Each client will authenticate with a GitBook API token and can specify an organization or space context to scope operations. Typical workflows include listing organizations and spaces, exploring space content and pages, retrieving page content, and running AI prompts to analyze, summarize, or optimize documentation.

How to install

Prerequisites you need before installing:

• Node.js 20+
• npm
• GitBook API token (generate at the GitBook developer portal)

Clone the MCP server repository, install dependencies, and set up the local environment, then run the development server.

Install steps

# Clone the MCP server repository
git clone https://github.com/rickysullivan/gitbook-mcp.git
cd gitbook-mcp

# Install dependencies
npm install

# Set up local development environment (optional but recommended)
npm run setup

# Add your GitBook API token for development only
# Create a local environment file and export the token
# Example: echo "GITBOOK_API_TOKEN=gb_api_your_token_here" > .env.local

Start the server for development

npm run dev

Configuration and usage notes

Use the following environment variables and CLI arguments to configure the MCP server for your workspace. The API token is required, while organization and space identifiers can be set as defaults or provided per request.

Environment and runtime options

Environment variables you may configure in your local environment or in an .env file include: GITBOOK_API_TOKEN, GITBOOK_ORGANIZATION_ID, and GITBOOK_SPACE_ID. You can also pass --organization-id and --space-id on startup to set defaults for the session.

Additional sections

Configuration options include: CLI arguments, embedded configuration files, and environment variables. If you use a default organization or space, tools marked as optional will omit corresponding IDs and automatically use the configured defaults. Explicit parameters override defaults.

Security considerations

Keep your GitBook API token secure. Do not commit tokens to version control. Use environment-specific configurations (like local .env files or environment variables in your deployment platform) to supply the token at runtime.

Troubleshooting tips

If you encounter authentication or permission issues, verify that the API token is correct and has access to the target organization and spaces. For misconfigurations, confirm that the organization and space IDs (if used) exist and that your token is active.

Prompts and tools overview

The server offers 6 AI-powered prompts to support documentation workflows and 12 tools for content operations. You can fetch documentation topics, analyze gaps, audits, and summaries, and perform content optimization.

Examples of typical commands to start a client connection

Connect via an IDE or assistant using a configuration that points to the local or remote MCP endpoint and passes the required authentication token. Each client configuration should specify the server command, arguments, and environment variables as shown in the supported examples.

Available tools

list_organizations

Lists all accessible GitBook organizations.

list_spaces

Lists spaces, optionally filtered by organization.

get_space

Retrieves detailed information about a specific space.

get_space_content

Retrieves the content structure and pages of a space.

search_content

Searches for content within a space using full-text search.

get_page_content

Retrieves the content of a specific page.

get_page_by_path

Retrieves page content using the page path.

get_space_files

Lists all files in a space.

get_file

Retrieves details of a specific file.

list_collections

Lists all accessible collections.

get_collection

Retrieves details of a specific collection.

get_collection_spaces

Lists all spaces within a collection.

fetch_documentation

Fetches and analyzes GitBook documentation content for specific topics.

analyze_content_gaps

Identifies gaps and missing content in documentation.

content_audit

Performs quality audits of documentation content.

documentation_summary

Generates comprehensive summaries of GitBook spaces.

content_optimization

Optimizes content for SEO, readability, structure, or performance.