GitBook
A GitBook documentation MCP server that automatically scrapes and indexes GitBook sites to provide AI assistants with searchable access to documentation content. Built with TypeScript and SQLite for fast full-text search, it features intelligent domain detection that automatically configures server names and tool prefixes based on the documentation content, advanced text processing with stemming and fuzzy matching, and both stdio and HTTP transport modes. The server includes a web UI for managing multiple documentation sources, supports code block extraction and markdown formatting, and uses persistent caching to minimize scraping overhead, making it valuable for teams who need AI assistants to quickly reference and search through their GitBook documentation during development workflows.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/tcsenpai/mcpbook
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve GitBook from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.