📚 resourceActivePromisingmedium

jcodemunch-mcp

The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing

Stars

1.9k

Skill Type

📖 Library & API Reference

Quality Score

82/200

License

Unknown

Forks

295

Last Updated

Jun 11, 2026

Discovered

Mar 26, 2026

Validation

Passed

github.com/jgravelle/jcodemunch-mcp

Quality Breakdown

82/ 200

Content Signals

○Gotchas/Edge Cases+40

○Progressive Disclosure+30

○Trigger Description+20

○Verification/Safety+20

✓Code Examples+15

✓Composability+15

Repo Health

✓Recent Activity+15

○Scripts/Automation+10

○Real Usage (Issues)+10

✓Single Responsibility+10

○Config/Persistence+10

✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Contains CLAUDE.md file which may persist agent configuration or memory state
Includes Docker and docker-compose.yml files enabling containerized execution
Contains shell scripts (packaging/debian/build_deb.sh) for system-level operations
Includes CLI tools (cli/cli.py, munch-bench/munch_bench/cli.py) that could execute arbitrary code
Contains benchmark harnesses and replay mechanisms that could execute external code
AGENT_HOOKS.md and AGENTS.md suggest agent automation capabilities without clear human approval gates