The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing
{
"mcpServers": {
"jdocmunch": {
"args": [
"jdocmunch-mcp"
],
"type": "stdio",
"command": "uvx"
},
"jcodemunch": {
"args": [
"jcodemunch-mcp"
],
"type": "stdio",
"command": "uvx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing
Is it safe?
No known CVEs for jcodemunch-mcp.
No authentication — any process on your machine can connect.
License not specified.
Is it maintained?
Last commit 1 days ago. 1,479 stars.
Will it work with my client?
Transport: stdio, sse, http. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
Context cost
9 tools. ~400 tokens (0.2% of 200K).
This server supports HTTP transport. Be the first to test it — help the community know if it works.
No known vulnerabilities.
search_symbolsSearch for symbols in the indexed codebase using BM25-based symbol search and fuzzy matching
get_symbol_sourceRetrieve the exact source code implementation of a symbol with byte-level precision
get_ranked_contextRetrieve query-driven token-budgeted context assemblies for symbols
find_dead_codeDetect dead code in the codebase
get_changed_symbolsMap git diffs to symbols to identify changed code elements
get_symbol_importanceRetrieve architectural centrality ranking of symbols using PageRank
find_importersFind all places that import or reference a given symbol
get_blast_radiusCalculate blast-radius depth scoring for code changes
get_class_hierarchyTraverse and retrieve class hierarchy relationships
This server is missing a description.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
An open-source AI agent that brings the power of Gemini directly into your terminal.
The full-stack TypeScript framework to build, test, and deploy production-ready MCP servers and AI-native apps.
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
MCP Security Weekly
Get CVE alerts and security updates for Jcodemunch Mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Quickstart - https://github.com/jgravelle/jcodemunch-mcp/blob/main/QUICKSTART.md
<!-- mcp-name: io.github.jgravelle/jcodemunch-mcp -->Use it to make money, and Uncle J. gets a taste. Fair enough? details
| Doc | What it covers | |-----|----------------| | QUICKSTART.md | Zero-to-indexed in three steps | | USER_GUIDE.md | Full tool reference, workflows, and best practices | | AGENT_HOOKS.md | Agent hooks and prompt policies | | ARCHITECTURE.md | Internal design, storage model, and extension points | | LANGUAGE_SUPPORT.md | Supported languages and parsing details | | CONTEXT_PROVIDERS.md | dbt, Git, and custom context provider docs | | TROUBLESHOOTING.md | Common issues and fixes |
Most AI agents explore repositories the expensive way:
open entire files → skim thousands of irrelevant lines → repeat.
That is not “a little inefficient.” That is a token incinerator.
jCodeMunch indexes a codebase once and lets agents retrieve only the exact code they need: functions, classes, methods, constants, outlines, and tightly scoped context bundles, with byte-level precision.
In retrieval-heavy workflows, that routinely cuts code-reading token usage by 95%+ because the agent stops brute-reading giant files just to find one useful implementation.
| Task | Traditional approach | With jCodeMunch | | ---------------------- | ------------------------- | ------------------------------------------- | | Find a function | Open and scan large files | Search symbol → fetch exact implementation | | Understand a module | Read broad file regions | Pull only relevant symbols and imports | | Explore repo structure | Traverse file after file | Query outlines, trees, and targeted bundles |
Index once. Query cheaply. Keep moving. Precision context beats brute-force context.
[Full recognition page →](https://j.gravelle.us/jCodeMunch/recog