The reputation layer for AI skills, tools & agents

jgravelle/jcodemunch-mcp

Score: 61.3 Rank #68

Token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing

Overview

jgravelle/jcodemunch-mcp is a Python MCP server. Token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing

Ranked #68 out of 25632 indexed tools.

In the top 1% of all indexed tools.

Has 1,082 GitHub stars.

Has 21 contributors.

Actively maintained with commits in the last week.

Ecosystem

Python No license

Signal Breakdown

Stars 1,082
Freshness 2d ago
Issue Health 96%
Contributors 21
Dependents 0
Forks 196
Description Good
License None

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

License low impact

Add an MIT or Apache-2.0 license to signal trust and enable adoption

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge

AgentRank score for jgravelle/jcodemunch-mcp
[![AgentRank](https://agentrank-ai.com/api/badge/tool/jgravelle--jcodemunch-mcp)](https://agentrank-ai.com/tool/jgravelle--jcodemunch-mcp)
<a href="https://agentrank-ai.com/tool/jgravelle--jcodemunch-mcp"><img src="https://agentrank-ai.com/api/badge/tool/jgravelle--jcodemunch-mcp" alt="AgentRank"></a>

Matched Queries

"mcp server""mcp-server"

From the README

## FREE FOR PERSONAL USE
**Use it to make money, and Uncle J. gets a taste. Fair enough?** [details](#commercial-licenses)

## Cut code-reading token costs by up to **99%**

Most AI agents explore repositories the expensive way:
open entire files → skim thousands of irrelevant lines → repeat.

**jCodeMunch indexes a codebase once and lets agents retrieve only the exact symbols they need** — functions, classes, methods, constants — with byte-level precision.

| Task                   | Traditional approach | With jCodeMunch |
| ---------------------- | -------------------- | --------------- |
| Find a function        | ~40,000 tokens       | ~200 tokens     |
| Understand module API  | ~15,000 tokens       | ~800 tokens     |
| Explore repo structure | ~200,000 tokens      | ~2k tokens      |

Index once. Query cheaply forever.  
Precision context beats brute-force context.

---

# jCodeMunch MCP

### Structured retrieval for serious AI agents

> ## Commercial licenses
> jCodeMunch-MCP 
Read full README on GitHub →
Are you the maintainer? Claim this listing