by semgrep · MCP Server · ★ 687
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is mcp safe to install? View the security audit →
⚠️ The Semgrep MCP server has been moved from a standalone repo to the main repository! ⚠️ This repository has been deprecated, and further updates to the Semgrep MCP server will be made via the official binary. Semgrep MCP
uvx semgrep-mcp # see --help for more options
docker run -i --rm ghcr.io/semgrep/mcp -t stdio
Taken from the project's README on GitHub. Check the security audit before running it.
No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
| Stars | 687 |
| Forks | 58 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 75.2977850694175/100 |
| Open Issues | 28 |
| Last Updated | 2025-10-28 |
| Created | 2025-03-17 |
| Platforms | mcp, python |
| Est. Tokens | ~62k |
These tools work well together with mcp for enhanced workflows:
Explore other popular mcp server tools:
mcp is A MCP server for using Semgrep to scan code for security vulnerabilities.. It is categorized as a MCP Server with 687 GitHub stars.
mcp is primarily written in Python. It covers topics such as mcp, semgrep.
The README on GitHub (github.com/semgrep/mcp) gives: uvx semgrep-mcp # see --help for more options , then docker run -i --rm ghcr.io/semgrep/mcp -t stdio. Usage details are in the same README.
mcp is released under the MIT license, making it free to use and modify according to the license terms.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: