Jdocmunch Documentation Retrieval

v1.4.2Search & Data Extractionstable

The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing

claudeclaude-codedocsdocumentationllm
Share:
175
Stars
0
Downloads
0
Weekly
0/5

What is Jdocmunch Documentation Retrieval?

Jdocmunch Documentation Retrieval is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to leading, most token-efficient mcp server for documentation exploration and retrieval via structured section indexing

The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing

This server falls under the Search & Data Extraction category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • The leading, most token-efficient MCP server for documentati

Use Cases

Token-efficient documentation search
Structured section indexing
Fast documentation lookup
jgravelle

Maintainer

LicenseNOASSERTION
Languagepython
Versionv1.4.2
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

PIP

pip install jdocmunch-mcp

Manual Installation

pip install jdocmunch-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Jdocmunch Documentation Retrieval

jDocMunch (`jdocmunch-mcp`) is a token-efficient MCP server for documentation exploration and retrieval that indexes local documentation directories or GitHub repositories into structured sections, then exposes targeted tools for navigating, searching, and fetching specific documentation content. Instead of dumping entire README files into context, it lets AI assistants fetch only the relevant sections they need, with each response reporting how many tokens were saved versus a naive full-document approach. Developers and AI workflows use it to give Claude or other agents precise access to large documentation sets — including third-party SDKs, internal wikis, or open-source project docs — without blowing through context budgets.

Prerequisites

  • Python 3.9 or later installed
  • pip or pipx for installation
  • A GitHub personal access token (set as `GITHUB_TOKEN`) if indexing private or rate-limited repositories
  • An optional API key for embedding providers: `ANTHROPIC_API_KEY` (Claude Haiku summaries), `GOOGLE_API_KEY` (Gemini embeddings), or `OPENAI_API_KEY` (OpenAI embeddings)
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Install jdocmunch-mcp

Install the package from PyPI. The `jdocmunch-mcp` command will be available after installation.

pip install jdocmunch-mcp
# Verify installation:
jdocmunch-mcp --help
2

Set environment variables for optional features

Configure API keys for embedding and summarization providers you want to use. At minimum, set `GITHUB_TOKEN` if you plan to index GitHub repositories.

export GITHUB_TOKEN=ghp_your_github_token
export ANTHROPIC_API_KEY=sk-ant-your-key  # optional, for section summaries
export GOOGLE_API_KEY=your-key             # optional, for Gemini embeddings
3

Index a documentation repository

Index a GitHub repository's documentation so jDocMunch can serve it section by section. You can also index local directories using `index_local`.

jdocmunch-mcp index-local /path/to/your/docs
4

Add the server to your MCP client configuration

Register jdocmunch-mcp in your Claude Desktop or Claude Code configuration. Pass environment variables in the env block.

{
  "mcpServers": {
    "jdocmunch": {
      "command": "jdocmunch-mcp",
      "args": ["serve"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_github_token",
        "ANTHROPIC_API_KEY": "sk-ant-your-key"
      }
    }
  }
}
5

Restart your MCP client and explore documentation

Restart Claude Desktop or your MCP client. You can now ask the AI to search for documentation sections, retrieve specific content, or explore the table of contents of indexed repositories.

Jdocmunch Documentation Retrieval Examples

Client configuration

Claude Desktop configuration for the jDocMunch MCP server with GitHub token for repository indexing.

{
  "mcpServers": {
    "jdocmunch": {
      "command": "jdocmunch-mcp",
      "args": ["serve"],
      "env": {
        "GITHUB_TOKEN": "ghp_your_github_personal_access_token",
        "ANTHROPIC_API_KEY": "sk-ant-your-anthropic-api-key"
      }
    }
  }
}

Prompts to try

Example prompts for documentation retrieval using jDocMunch's search and section tools.

- "Index the repository anthropics/anthropic-sdk-python and show me the table of contents"
- "Search the indexed docs for sections about authentication"
- "Get the section on 'streaming responses' from the Anthropic SDK docs"
- "List all repositories that have been indexed"
- "Check for broken links in the documentation for owner/repo"

Troubleshooting Jdocmunch Documentation Retrieval

GitHub repository indexing fails with rate limit or 403 error

Set the `GITHUB_TOKEN` environment variable to a valid GitHub personal access token. For private repositories, ensure the token has `repo` scope. Unauthenticated GitHub API calls are heavily rate-limited.

Search returns no results after indexing

Confirm the index completed successfully by running `jdocmunch-mcp index-local <path>` from the command line and checking for errors. The `DOC_INDEX_PATH` variable can be set to a custom cache location if the default path has permission issues.

Embedding provider errors on startup

Set `JDOCMUNCH_EMBEDDING_PROVIDER=none` to disable embeddings if you don't have an API key, or set it to `sentence-transformers` to use local embeddings without an API key. Install the `sentence-transformers` package separately if using that option.

Frequently Asked Questions about Jdocmunch Documentation Retrieval

What is Jdocmunch Documentation Retrieval?

Jdocmunch Documentation Retrieval is a Model Context Protocol (MCP) server that leading, most token-efficient mcp server for documentation exploration and retrieval via structured section indexing It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Jdocmunch Documentation Retrieval?

Install via pip with: pip install jdocmunch-mcp. Then configure your AI client to connect to this MCP server.

Which AI clients work with Jdocmunch Documentation Retrieval?

Jdocmunch Documentation Retrieval works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Jdocmunch Documentation Retrieval free to use?

Yes, Jdocmunch Documentation Retrieval is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.

Browse More Search & Data Extraction MCP Servers

Explore all search & data extraction servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "jdocmunch": { "command": "pip", "args": ["install", "jdocmunch-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Jdocmunch Documentation Retrieval?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides