MkDocs Search
MkDocs MCP Server provides search functionality for any MkDocs-powered documentation site by leveraging the existing Lunr.js search implementation. Developed by Serverless DNA, this TypeScript server fetches and caches search indexes from MkDocs sites, converts HTML content to markdown, and offers tools for searching documentation and retrieving full page content. The implementation features efficient caching mechanisms with ETag validation, version-specific documentation support, and a modular architecture with services for fetching, logging, and markdown conversion. Particularly valuable for users who need to access documentation directly through AI assistants without navigating documentation websites manually.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/serverless-dna/mkdocs-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve MkDocs Search 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.