kapilduraphe / mcp-watch
A comprehensive security scanner for Model Context Protocol (MCP) servers that detects vulnerabilities and security issues in your MCP server implementations.
Why this job: name: mcp; says: mcp server; topics: mcp, model context protocol
What it does
- Credential Detection. Finds hardcoded API keys, tokens, and insecure credential storage
- Tool Poisoning. Detects hidden malicious instructions in tool descriptions
- Parameter Injection. Identifies magic parameters that extract sensitive AI context
- Prompt Injection. Scans for prompt manipulation and injection attacks
- Tool Mutation. Detects dynamic tool changes and rug-pull risks
Get started
# Scan without installing anything
docker run --rm mcp-watch scan https://github.com/user/mcp-server
docker run --rm -v $(pwd):/workspace mcp-watch scan-local /workspace npm install -g mcp-watch- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 139
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- TypeScript
- 96% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 33% closed
- 6 still open
- Pull requests
- 21 merged
- 6 waiting
- Releases
- None
- Never published
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| modelcontextprotocol / python-sdk | 24,835 | 7 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- TypeScript 96%
- Dockerfile 2%
- JavaScript 2%
Topics
- agentic-ai
- anthropic
- mcp
Project record
- JobMCP servers
- StatusListed
- Commits23
- Forks19
- Watching1
- Stars in 28 days+1
- CreatedMay 29, 2025
- First seen by usNov 7, 2026
- CheckedNov 12, 2026