Rowan MCP server
Commit Nov 15, 2026Performs static security analysis on source code, model files, dependencies, and MCP configurations to identify vulnerabilities without executing code.
Also known as hedgerow-dev/rowan
- Stars
- 5
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 15, 2026
- License
- MIT
What is Rowan MCP?
Rowan performs static security analysis on source code, model files, dependencies, and MCP configurations to identify vulnerabilities without executing code.
Summary generated from the project's README
About Rowan MCP server
Identifying security vulnerabilities in source code and AI/ML projects is what Rowan enables for developers and coding agents. It performs static analysis to detect issues like injection, unsafe deserialization, SSRF, and leaked secrets without ever executing the code. The tool is designed to be used locally via terminal commands or integrated into AI agents like Claude Code, Codex, or Cursor that can run shell instructions.
Users install the server using pipx or uv and must also install the Opengrep scan engine. The analysis covers a wide range of targets including Python and JS/TS source code, model files like Pickle or SafeTensors, and MCP configurations. While the standard scan remains offline, users can opt to check dependencies for known CVEs by omitting the --no-sca flag. This process provides a report of findings that serves as a lead for manual review rather than a definitive list of confirmed bugs.
What you can do with it
- 1Scan AI/ML projects for risksAn AI agent can scan a repository to find unsafe model loading or risky agent tools.
- 2Automate security in CI pipelinesDevelopers can configure the tool to exit with a failure code when high or critical findings are detected during a build.
- 3Perform offline dependency auditsYou can run a scan that avoids all network calls to ensure your code and dependencies are analyzed privately.
- 4Track new security regressionsUse baseline files to record current findings so that future scans only report newly introduced issues.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablehedgerow-dev/rowan is public and reachablegithub.com/hedgerow-dev/rowan ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-24github.com/hedgerow-dev/rowan ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubRowan
Find security issues in your code and AI/ML projects, with evidence you can review.
Rowan reads your project's source code and model files and reports likely vulnerabilities: injection, unsafe deserialization, SSRF, leaked secrets, risky agent tools, unsafe model loading and more. It never runs your code.
Alpha. Treat every finding as a lead to check, not a confirmed bug. A clean report does not prove a project is secure.
Quick start
You need Python 3.10+ and pipx, which installs
command-line tools into their own environment (on macOS: brew install pipx,
then pipx ensurepath and open a new terminal).
1. Install Rowan:
pipx install rowan-sast
Already use uv? uv tool install rowan-sast works too. A plain
pip install fails on Homebrew Python by design; see
getting started for a virtual-environment install.
2. Install the scan engine (Opengrep) and check it:
rowan install-engine
export PATH="$HOME/.local/bin:$PATH"
rowan self-test
self-test should print [OK] three times.
3. Scan a project:
rowan scan /path/to/your-project
Windows, troubleshooting and more detail: getting started.
Let your coding agent do it
Paste this into Claude Code, Codex, Cursor or any agent that can run terminal commands, with your project open:
Install Rowan and scan this project for security issues.
1. Install it in its own folder (not inside this project) by following
https://github.com/hedgerow-dev/rowan/blob/main/docs/getting-started.md
2. Run `rowan self-test`. If the engine is not [OK], stop and tell me.
3. Run: rowan scan <this project's absolute path> --no-project-config
--no-sca --audit -f json -o <a folder outside this project>/rowan-report.json
4. If summary.degraded is true, tell me the scan is incomplete and why.
5. List the High and Critical findings with file:line links. For each one,
say whether you checked the code or it is still just a lead.
6. Do not change any code in this project.
--no-sca keeps this first scan offline. Drop it to also check your
dependencies for known CVEs (this sends package names and versions to OSV).
Common commands
rowan scan PATH # readable report
rowan scan PATH --audit # include low-severity findings
rowan scan PATH -f json -o report.json # save a report (also: html, sarif)
rowan scan PATH --ci --severity high # CI: exit 1 on high/critical findings
rowan scan PATH --write-baseline base.json # record today's findings...
rowan scan PATH --ci --baseline base.json # ...then report only new ones
With --ci, exit code 0 means no findings, 1 means findings, and 2
means the scan was incomplete. Reports can contain source code and secrets:
review them before sharing.
What it checks
| Area | Coverage |
|---|---|
| Source code | Injection, unsafe deserialization, path traversal, SSRF, XSS, secrets |
| AI/ML apps | Model loading, agent tools, LLM output handling, prompt files, MCP config |
| Dataflow | Within-file through Opengrep; cross-file for Python and JS/TS, limited for Go |
| Dependencies | Known CVEs, reachability hints, CycloneDX SBOM and OpenVEX output |
| Model files | Pickle, PyTorch, GGUF, SafeTensors, Keras, ONNX, TensorFlow, numpy, joblib (via Hayward) |
Python and JS/TS get the deepest analysis. Java, Kotlin and C# get within-file dataflow. Ruby, PHP and Rust get limited pattern checks. The report lists what it could not analyze.
The rule catalog has 573 rules across 51 YAML files. That is 358 regex rules and 215 taint rules (Opengrep). See the rule catalog.
Privacy
rowan scan never calls an LLM or uploads your code. Its only network calls
are dependency lookups (OSV and FIRST EPSS), which --no-sca turns off.
The experimental rowan hunt command does send code to the LLM you configure:
see the usage guide.
More
- Getting started: install, first scan, MCP setup, troubleshooting
- Capabilities: what Rowan finds, how it compares, measured results
- Usage guide: every option, configuration, baselines, CI and GitHub Action
- Contributing and architecture
- Security policy: report a vulnerability in Rowan privately
License
MIT. Opengrep is a separate LGPL-2.1 engine and is not bundled.
Rowan MCP questions
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.