# Rowan MCP server

> Performs static security analysis on source code, model files, dependencies, and MCP configurations to identify vulnerabilities without executing code.

- Repository: https://github.com/hedgerow-dev/rowan
- Page: https://hostedmcp.org/servers/hedgerow-dev/rowan
- Transport: —
- Stars: 5
- License: MIT

## FAQ

### Does Rowan run my code during a scan?

No, Rowan is a static analysis tool that reads your project files without executing them.

### Does scanning my project upload my code to an LLM?

No, the standard scan never calls an LLM or uploads your code; network calls are limited to dependency lookups unless using the experimental hunt command.

### What kind of AI/ML vulnerabilities does it detect?

It checks for issues in model loading, agent tools, LLM output handling, prompt files, and MCP configurations.

### Can I use Rowan in a CI/CD pipeline?

Yes, it includes a CI mode that returns specific exit codes based on findings or scan completeness.
