jgravelle/jdocmunch-mcp
The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing
Indexes documentation by heading hierarchy and section structure, enabling byte-precise retrieval of individual sections rather than entire files—reducing token consumption by 98% on typical tasks. Implements the jMRI-Full specification with stable section IDs, local-first storage, and format-aware parsing (Markdown, OpenAPI, JSON, XML, Jupyter). Works as an MCP server with Claude Desktop, Claude Code, and other compatible agents via stdio transport.
90 stars and 12,005 monthly downloads. Available on PyPI.
Stars
90
Forks
22
Language
Python
License
—
Category
Last pushed
Mar 19, 2026
Monthly downloads
12,005
Commits (30d)
0
Dependencies
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/jgravelle/jdocmunch-mcp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related servers
augmnt/augments-mcp-server
Comprehensive MCP server providing real-time framework documentation access for Claude Code with...
regenrek/deepwiki-mcp
📖 MCP server for fetch deepwiki.com and get latest knowledge in Cursor and other Code Editors
andrea9293/mcp-documentation-server
MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management •...
spences10/mcp-svelte-docs
🔍 MCP server that lets you search and access Svelte documentation with built-in caching
drewburchfield/help-scout-mcp-server
MCP server for Help Scout - search conversations, threads, and inboxes with AI agents