jDocmunch MCP
Most agents still burn thousands of tokens dumping entire documentation files into context to find one config block. This server indexes docs once by section hierarchy, then lets you search and retrieve at heading granularity with byte-precise extraction. It parses Markdown, reStructuredText, AsciiDoc, Jupyter notebooks, HTML, YAML, JSON, and OpenAPI specs into stable section IDs that survive re-indexing. Tools cover discovery, structure browsing, semantic search, and single or batch retrieval. Sections include summaries, tags, content hashes, and parent/child wiring. Implements jMRI-Full with local-first storage under `~/.doc-index/`. Built for workflows where you need agents to navigate technical docs structurally instead of grep-and-pray or brute-force file reading.
- GitHub stars
- 206
- tools
- 6
- transport
- STDIO
- last updated
- Nov 5, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
search_sectionsSearch documentation by section, returning ranked metadata.
Search documentation by section, returning ranked metadata.
No parameter schema in public metadata yet.
get_sectionFetch the full content of one section by byte-precise extraction from the original file.
Fetch the full content of one section by byte-precise extraction from the original file.
No parameter schema in public metadata yet.
get_toc_treeStructural view of the whole indexed documentation corpus.
Structural view of the whole indexed documentation corpus.
No parameter schema in public metadata yet.
index_localIndex a local documentation folder.
Index a local documentation folder.
No parameter schema in public metadata yet.
index_repoIndex documentation from a GitHub repository.
Index documentation from a GitHub repository.
No parameter schema in public metadata yet.
jdocmunch_guideGuide for how the agent should use the doc-exploration tools.
Guide for how the agent should use the doc-exploration tools.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
jDocMunch MCP
jDocMunch is an MCP server for coding agents that retrieves the exact documentation section a task needs, without loading whole files into the context window.
Index a documentation set once by heading hierarchy, then fetch a single section, a heading subtree, or a ranked search result — extracted byte-precisely from the original file.
Install · Quickstart · Benchmarks · Commercial licensing
Details
- Repository
- github.com/jgravelle/jdocmunch-mcp
- Categories
- Search & Web Crawling, Data & Analytics
- Package
jdocmunch-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from jgravelle
Related Search & Web Crawling MCP servers
View all
Mcp Sap Docsmarianfoo/mcp-sap-docsFast MCP server for unified SAP docs search (SAPUI5, CAP, OpenUI5, wdi5) with BM25 full-text search196stars
Zotero MCPkujenga/zotero-mcpSearch your Zotero library, retrieve item metadata, and read full text from AI assistants.162stars
Code Context Engineelara-labs/code-context-engineIndex your codebase. AI searches instead of re-reading files. 94% token savings.160stars
Jjlabsio Korea Stock Mcpjjlabsio/korea-stock-mcpSearch company disclosures and financial statements from the Korean market. Retrieve stock profile…144stars
Oxylabs Mcpoxylabs/oxylabs-mcpFetch and process content from specified URLs & sources using the Oxylabs Web Scraper API.104stars
Clinicaltrialsgov Mcp Servercyanheads/clinicaltrialsgov-mcp-serverSearch ClinicalTrials.gov: find studies, retrieve results, match patients to candidate trials.100stars