Repo Intelligence Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Repo Intelligence Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
An MCP server that gives LLMs structured, read-only insight into local code repositories — directory tree, languages, dependencies, scripts, and config files.
| URI | Description |
|---|---|
repo://tree | Directory tree (like tree command) |
repo://languages | Detected languages by file count |
repo://dependencies | Dependencies from package.json, requirements.txt, pyproject.toml |
repo://scripts | npm scripts and Makefile targets |
repo://configs | Detected config files (ESLint, Prettier, tsconfig, CI, etc.) |
Requirements: Node.js ≥ 18
git clone https://github.com/georg-nikola/repo-intelligence-mcp
cd repo-intelligence-mcp
npm install
npm run buildclaude mcp add repo-intelligence -- node /path/to/repo-intelligence-mcp/dist/server.js --repo /path/to/your/repoAdd to claude_desktop_config.json:
{
"mcpServers": {
"repo-intelligence": {
"command": "node",
"args": ["/path/to/repo-intelligence-mcp/dist/server.js", "--repo", "/path/to/your/repo"]
}
}
}| Flag | Default | Description |
|---|---|---|
--repo | cwd | Path to the repository to analyze |
--max-files | 50000 | Maximum files to scan |
--max-depth | 10 | Maximum directory depth |
npm run dev # run without build step
npm test # run tests
npm run lint # type-checkMIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.