JDocmunch MCP

What jDocmunch MCP does

jDocmunch MCP turns documentation files into a searchable collection of sections rather than treating each file as the smallest retrieval unit. It supports .md, .rst, .adoc, .ipynb, .html, .yaml, .json, and OpenAPI documents. Documentation can be indexed from a local directory or directly from a GitHub repository.

The server is designed for coding agents that need a narrowly scoped answer from a larger documentation set. A request such as an authentication or configuration lookup can return the relevant section without placing the entire source file into the model context.

How it works

During indexing, jDocmunch MCP parses heading hierarchy and records byte offsets into the original files. Retrieval then reads the requested content from those offsets, preserving the source section rather than generating a reformatted excerpt. Sections can retain stable identities across re-indexing when their path, heading text, and heading level stay the same.

A typical workflow indexes a documentation folder, searches for a topic with search_sections, and passes the best result to get_section. The server also supports structural browsing through get_toc_tree. Search results can include compact output or snippets to reduce the need for a follow-up retrieval call.

Setup and configuration

Python 3.10 or newer and an MCP-compatible client are required. The package can be installed with:

uv tool install jdocmunch-mcp
jdocmunch-mcp init

For an ephemeral setup, run uvx jdocmunch-mcp. pipx and a manually managed virtual environment with pip are also supported. The init command can detect MCP clients, write configuration entries, install the documentation guidance prompt, and optionally set up hooks or index documentation.

Registering the server makes its tools available, but agents may still need explicit guidance to use them. The project recommends adding a jdocmunch_guide instruction to the agent's project configuration. Large indexes can be built from the shell with jdocmunch-mcp index-local, avoiding an MCP client tool-call timeout. DOC_INDEX_PATH can be set in both the client configuration and shell when using a custom index location.

Tools and capabilities

• search_sections finds ranked documentation sections.
• get_section retrieves one section from the original file.
• get_toc_tree exposes the indexed heading structure.
• index-local indexes a local documentation folder.
• index_repo indexes documentation from a GitHub repository.
• Indexing supports file limits, path selection, ignore patterns, and optional embeddings.

A local folder is capped at 10,000 files by default, with CLI options to raise the limit or narrow the indexed paths. Embeddings can be skipped for an initial lexical index and added during a later rebuild.

Limitations and notes

Commercial use requires a paid license; personal use is free. Scanned PDFs need the optional OCR extra and an OCR engine already installed on the machine. jDocmunch MCP does not install or download that engine, language pack, or model. Indexing very large folders may exceed a client's tool timeout, so the command-line indexer is the appropriate fallback.

Section-level savings depend on the size of the containing file and the requested section. A small file or broad section may provide little reduction. The project reports benchmark results by corpus rather than as a universal performance guarantee, and its retrieval-quality release gate uses an nDCG threshold of 0.95 on a frozen replay fixture.