Semgrep MCP server

This is a helper from Semgrep, a company that makes a tool for finding security problems in code. Once it is connected, your AI assistant can run Semgrep checks on the code it writes or on files you point it at. It is handy for developers, but also for anyone who asks an AI to write code and wants a second pair of eyes on safety.

What this MCP server does

You ask your AI to check some code for security problems. The AI uses this helper, which runs Semgrep on the code. Semgrep looks through the code using thousands of built-in rules and reports anything suspicious. The AI then shows you what it found, in plain words, right in the chat. If you use it inside a coding tool like Claude Code or Cursor, it can also scan each file the AI writes and ask the AI to fix problems before you accept the code.

Click to zoom

What you can do with it

• Scan a piece of code you paste in for security issues
• Check files in your project for known bad patterns
• Look for leaked secrets like passwords or keys in code
• Flag risky dependencies in your project
• Get a short explanation of each finding in the chat
• Ask the AI to rewrite code until the scan comes back clean

Try asking your AI

• “Scan this Python file for security problems and explain what you find”
• “Check my project folder for any hardcoded passwords or API keys”
• “Look at the code you just wrote and fix anything Semgrep flags”
• “Are there any risky patterns in this JavaScript snippet?”

What it gives back to you

You get a list of findings, each with the file and line where the problem is, a short description, and a severity level. The AI usually summarises them in plain words and can suggest fixes. If nothing is found, it tells you the scan came back clean. In coding tools, it can also show the scan result before you accept a change.

Before you start

Who it's for

Developers and anyone who uses an AI to write code and wants a quick security check before using it.