Sponsored by Deepsite.site

Gitbook MCP

Created By
rickysullivan8 months ago
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.
Content

GitBook MCP Server Reference

A Model Context Protocol (MCP) server that provides access to GitBook's API for AI assistants and LLM applications.

Overview

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.

Quick Setup

Prerequisites

IDE and AI Assistant Integration

VS Code (with GitHub Copilot)

Add to your VS Code MCP settings:

{
  "servers": {
    "gitbook-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["gitbook-mcp", "--organization-id=your_organization_id_here"],
      "env": {
        "GITBOOK_API_TOKEN": "gb_api_your_token_here"
      }
    }
  }
}

Claude Desktop

Add to your Claude Desktop configuration (%APPDATA%\Claude\claude_desktop_config.json on Windows or ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "gitbook-mcp": {
      "command": "npx",
      "args": ["gitbook-mcp", "--organization-id=your_organization_id"],
      "env": {
        "GITBOOK_API_TOKEN": "gb_api_your_token_here"
      }
    }
  }
}

See https://modelcontextprotocol.io/quickstart/user for details.

GitHub Copilot plugin for JetBrains IDEs (IntelliJ IDEA, WebStorm, etc.):

Add to your GitHub Copilot MCP settings for JetBrains IDEs (the path may vary by product and OS, e.g., ~/.config/github-copilot/intellij/mcp.json for IntelliJ on Linux/macOS, or the equivalent directory for your JetBrains IDE and platform):

{
  "servers": {
    "gitbook-mcp": {
      "command": "npx",
      "args": [
        "gitbook-mcp",
        "--organization-id=your_organization_id_here"
      ],
      "env": {
        "GITBOOK_API_TOKEN": "gb_api_your_token_here"
      }
    }
  }
}

JetBrains AI Assistant

Add to your JetBrains AI Assistant MCP configuration (see official docs for the exact path):

Getting Your GitBook Credentials

  1. API Token: Visit https://app.gitbook.com/account/developer to generate your API token
  2. Organization ID: Use the list_organizations tool after setup to find your organization ID
  3. Space ID (optional): Use the list_spaces tool (requires a valid organization ID and API token) to find specific space IDs
  4. Space ID (optional): Use the list_spaces tool to find specific space IDs

Configuration Options

You can configure the server using:

  • CLI arguments: --organization-id, --space-id
  • Environment variables in MCP config: Set via the env object in your MCP configuration
  • System environment variables: GITBOOK_API_TOKEN, GITBOOK_ORGANIZATION_ID, GITBOOK_SPACE_ID

Note: .env files are only supported when running the server locally for development, not when using npx gitbook-mcp.

API Reference

Tools

The GitBook MCP server provides 12 tools organized into functional categories. Each tool includes behavioral hints:

  • 📖 Read-only: Tool only reads data and doesn't modify anything
  • 🔄 Idempotent: Repeated calls with same args have no additional effect with the same result
  • 🌐 Open-world: Tool interacts with external entities

Organization Discovery

List Organizations (list_organizations) 📖 🔄 🌐

Lists all accessible GitBook organizations.

Parameters: None

Returns:

{
  "organizations": [
    {
      "id": "string",
      "title": "string",
      "urls": {
        "app": "string",
        "public": "string"
      }
    }
  ]
}

Space Management

List Spaces (list_spaces) 📖 🔄 🌐

Lists spaces, optionally filtered by organization.

Parameters:

  • organizationId (optional): Organization ID to filter spaces

Returns:

{
  "spaces": [
    {
      "id": "string",
      "title": "string",
      "visibility": "string",
      "urls": {
        "app": "string",
        "public": "string"
      }
    }
  ]
}
Get Space Details (get_space) 📖 🔄 🌐

Retrieves detailed information about a specific space.

Parameters:

  • spaceId (required): The ID of the space to retrieve

Returns:

{
  "id": "string",
  "title": "string",
  "description": "string",
  "visibility": "string",
  "urls": {
    "app": "string",
    "public": "string"
  }
}
Get Space Content (get_space_content) 📖 🔄 🌐

Retrieves the content structure and pages of a space.

Parameters:

  • spaceId (optional): The ID of the space (uses default if configured)

Returns:

{
  "pages": [
    {
      "id": "string",
      "title": "string",
      "slug": "string",
      "path": "string"
    }
  ]
}
Search Content (search_content) 📖 🔄 🌐

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

Parameters:

  • query (required): Search query string
  • spaceId (optional): The ID of the space to search (uses default if configured)

Returns:

{
  "results": [
    {
      "id": "string",
      "title": "string",
      "excerpt": "string",
      "url": "string"
    }
  ]
}

Content Retrieval

Get Page Content (get_page_content) 📖 🔄 🌐

Retrieves the content of a specific page.

Parameters:

  • pageId (required): The ID of the page to retrieve
  • spaceId (optional): The ID of the space containing the page
  • format (optional): Output format ("document" or "markdown", defaults to "document")
  • metadata (optional): Include revision metadata (boolean, defaults to false)
  • computed (optional): Include computed revision data (boolean, defaults to false)

Returns:

{
  "id": "string",
  "title": "string",
  "content": "string",
  "format": "string"
}
Get Page by Path (get_page_by_path) 📖 🔄 🌐

Retrieves page content using the page path.

Parameters:

  • pagePath (required): The path of the page to retrieve
  • spaceId (optional): The ID of the space containing the page

Returns:

{
  "id": "string",
  "title": "string",
  "content": "string",
  "path": "string"
}

File Management

Get Space Files (get_space_files) 📖 🔄 🌐

Lists all files in a space.

Parameters:

  • spaceId (optional): The ID of the space (uses default if configured)

Returns:

{
  "files": [
    {
      "id": "string",
      "name": "string",
      "downloadURL": "string",
      "size": "number"
    }
  ]
}
Get File Details (get_file) 📖 🔄 🌐

Retrieves details of a specific file.

Parameters:

  • fileId (required): The ID of the file to retrieve
  • spaceId (optional): The ID of the space containing the file

Returns:

{
  "id": "string",
  "name": "string",
  "downloadURL": "string",
  "size": "number",
  "uploadedAt": "string"
}

Collection Management

List Collections (list_collections) 📖 🔄 🌐

Lists all accessible collections.

Parameters:

  • organizationId (optional): Organization ID to filter collections

Returns:

{
  "collections": [
    {
      "id": "string",
      "title": "string",
      "description": "string"
    }
  ]
}
Get Collection Details (get_collection) 📖 🔄 🌐

Retrieves details of a specific collection.

Parameters:

  • collectionId (required): The ID of the collection to retrieve

Returns:

{
  "id": "string",
  "title": "string",
  "description": "string",
  "spaces": "number"
}
Get Collection Spaces (get_collection_spaces) 📖 🔄 🌐

Lists all spaces within a collection.

Parameters:

  • collectionId (required): The ID of the collection

Returns:

{
  "spaces": [
    {
      "id": "string",
      "title": "string",
      "visibility": "string"
    }
  ]
}

Prompts

The GitBook MCP server provides 6 AI-powered prompts for documentation workflows:

Fetch Documentation (fetch_documentation)

Fetches and analyzes GitBook documentation content for specific topics.

Parameters:

  • topic (required): The topic or subject to search for and analyze
  • spaceId (optional): The ID of the space to search (uses default if configured)
  • includeStructure (optional): Set to "true" to include space structure

Returns: A comprehensive analysis of documentation related to the specified topic, including:

  • Relevant pages and sections
  • Content summaries
  • Gaps or areas needing improvement

Analyze Content Gaps (analyze_content_gaps)

Identifies gaps and missing content in documentation.

Parameters:

  • spaceId (optional): The ID of the space to analyze (uses default if configured)
  • comparisonSource (optional): Source to compare against (default: "internal analysis")

Returns: A detailed gap analysis including:

  • Missing topics and incomplete sections
  • Coverage gaps prioritized by importance
  • Suggestions for new content areas

Content Audit (content_audit)

Performs quality audits of documentation content.

Parameters:

  • spaceId (optional): The ID of the space to audit (uses default if configured)
  • auditCriteria (optional): Specific criteria to audit (default: "general quality and consistency")

Returns: A comprehensive quality assessment including:

  • Content quality and consistency review
  • Outdated information identification
  • Writing style and formatting recommendations

Documentation Summary (documentation_summary)

Generates comprehensive summaries of GitBook spaces.

Parameters:

  • spaceId (optional): The ID of the space to summarize (uses default if configured)
  • summaryType (optional): Type of summary - "overview", "technical", "user-guide", or "custom" (default: "overview")

Returns: A structured summary including:

  • Space structure and content organization
  • Main topics and themes
  • Target audience and use cases

Content Optimization (content_optimization)

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

Parameters:

  • spaceId (optional): The ID of the space to optimize (uses default if configured)
  • optimizationType (required): Type of optimization - "SEO", "readability", "structure", or "performance"
  • targetMetrics (optional): Specific metrics or goals to optimize for

Returns: Optimization recommendations including:

  • Specific improvement strategies
  • Priority-ranked optimization opportunities
  • Implementation guidance

Configuration Reference

The GitBook MCP server supports multiple configuration methods with the following precedence (highest to lowest):

  1. CLI Arguments - Passed when starting the MCP server
  2. Configuration Files - Embedded in project configuration files
  3. Environment Variables - Set in .env.local or system environment

Environment Variables

VariableRequiredTypeDescription
GITBOOK_API_TOKENYesstringGitBook API token (obtain from https://app.gitbook.com/account/developer)
GITBOOK_ORGANIZATION_IDNostringDefault organization ID for operations
GITBOOK_SPACE_IDNostringDefault space ID for single-space projects

Note: Environment variables can be set in .env.local, .env, or your system environment.

CLI Arguments

ArgumentAliasTypeDescription
--organization-id--orgstringOrganization ID to work with
--space-id--spacestringDefault space for operations

Example:

node dist/index.js --organization-id your-org-id --space-id your-space-id

Additional Configuration Files

Typically these files are provided as context to the AI assistant, which means you can store project-based configuration.

  1. .github/copilot-instructions.md
  2. .cursorrules
  3. .cursor/rules/rules.md
  4. .cursor/rules/instructions.md

e.g.

Format:

## GitBook Configuration

For GitBook MCP operations, use the following configuration:
- organization-id: your-org-id-here
- space-id: your-space-id-here

Default Parameter Behavior

When GITBOOK_ORGANIZATION_ID or GITBOOK_SPACE_ID are configured:

  • Tools marked as "optional" can omit the corresponding ID parameters
  • The configured default values will be used automatically
  • Explicit parameters in tool calls override defaults

Development

Prerequisites

Installation & Setup

git clone https://github.com/rickysullivan/gitbook-mcp.git
cd gitbook-mcp
npm install
npm run setup
# Add your GITBOOK_API_TOKEN to .env.local (for local development only)

Development

npm run dev

Debugging

DEBUG=1 npm run dev

Add the MCP to VS Code for development

You will need to use node as the command when running locally. The first arg should be the path to the compiled JavaScript output (e.g., dist/index.js).

{
    "servers": {
        "gitbook-mcp-dev": {
            "type": "stdio",
            "command": "node",
            "args": [ "/my/path/to/gitbook-mcp/dist/index.js", "--organization-id=Luj2l6y6cIUPXJwbC574"],
            "env": {
                "GITBOOK_API_TOKEN": "gb_api_UHEGTNsMg0ONPTnm0LpsJNBCCikQyOMkBTtZNDAB"
            }
        }
    }
}

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.

npm run test

Error Handling

Common Error Codes

Error CodeDescriptionResolution
401Unauthorized - Invalid API tokenVerify GITBOOK_API_TOKEN is correct
403Forbidden - Insufficient permissionsCheck space/organization access permissions
404Not Found - Resource doesn't existVerify space/page/collection IDs are correct
429Rate Limited - Too many requestsImplement request throttling
500Internal Server ErrorCheck server logs for detailed error information

Troubleshooting

Token Issues:

  • Ensure token starts with gb_live_
  • Verify token has not expired
  • Check token permissions in GitBook settings

ID Resolution:

  • Use list_organizations to find valid organization IDs
  • Use list_spaces to find valid space IDs
  • Use get_space_content to find valid page IDs

Configuration Issues:

  • Verify environment variables are properly set
  • Check file permissions on configuration files
  • Ensure CLI arguments are properly formatted

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

License

MIT License - see the LICENSE file for details.

Server Config

{
  "mcpServers": {
    "gitbook-mcp": {
      "command": "npx",
      "args": [
        "gitbook-mcp",
        "--organization-id=your_organization_id"
      ],
      "env": {
        "GITBOOK_API_TOKEN": "gb_api_your_token_here"
      }
    }
  }
}
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Playwright McpPlaywright MCP server
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Tavily Mcp
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
ChatWiseThe second fastest AI chatbot™
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Serper MCP ServerA Serper MCP Server
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
DeepChatYour AI Partner on Desktop
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
CursorThe AI Code Editor
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Amap Maps高德地图官方 MCP Server
WindsurfThe new purpose-built IDE to harness magic
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。