jDocMunch MCP
An MCP server that indexes a documentation set by heading hierarchy and retrieves a single section, heading subtree or ranked search result, instead of loading whole files into an agent's context window.
jDocMunch parses a documentation set into a section tree keyed by its heading hierarchy, records each section's exact byte offsets in the source file, and exposes retrieval over MCP so a coding agent can fetch the installation section, one configuration block, or a specific heading subtree rather than an entire file. Sections keep durable identities across re-indexing as long as their path, heading text and heading level stay unchanged.
Benchmarks against public documentation corpora such as Kubernetes, SciPy, LangChain and a wiki report tens of thousands of tokens saved per query, with each result recorded alongside its corpus and date. It is free for personal use; commercial use requires a paid license.