semgrep-mcp

Use the following command to add the Semgrep MCP server to Claude Code:

claude mcp add semgrep uvx semgrep-mcp

Deploy the semgrep-mcp server using Helm. This chart uses the semgrep/mcp:main Docker image by default.

Run the following command to install the chart locally:

helm install my-semgrep-mcp ./chart/semgrep-mcp

To connect Semgrep to ChatGPT via the hosted SSE server:

1. Go to the Connector Settings page.
2. Name the connection Semgrep.
3. Set MCP Server URL to https://mcp.semgrep.ai/sse.
4. Set Authentication to No authentication.
5. Check the I trust this application checkbox.
6. Click Create.

Add the following configuration to your ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-specific) file to use uvx to run the server.

{
  "mcpServers": {
    "semgrep": {
      "command": "uvx",
      "args": ["semgrep-mcp"]
    }
  }
}

The server is available as a Docker image on GitHub Container Registry (ghcr.io/semgrep/mcp).

• For stdio mode: You must use -i (interactive) and specify -t stdio because the default container mode is SSE.
• For Streamable HTTP: Map port 8000 and use the -t streamable-http flag.
• For SSE mode: Map port 8000 and use the -t sse flag.

# Run in stdio mode
docker run -i --rm ghcr.io/semgrep/mcp -t stdio

# Run in Streamable HTTP mode
docker run -p 8000:8000 ghcr.io/semgrep/mcp -t streamable-http

# Run in SSE mode
docker run -p 8000:8000 ghcr.io/semgrep/mcp -t sse

To use Semgrep in Cursor, add the server to your mcp.json configuration. If you are using the local uvx method, you may need to provide a SEMGREP_APP_TOKEN in the environment variables.

Alternatively, you can use the Hosted Server (experimental) by adding a new MCP server in Cursor Settings (Cmd + Shift + J) with the type streamable-http and the URL https://mcp.semgrep.ai/mcp.

{
  "mcpServers": {
    "semgrep": {
      "command": "uvx",
      "args": ["semgrep-mcp"],
      "env": {
        "SEMGREP_APP_TOKEN": "<token>"
      }
    }
  }
}

The Semgrep MCP server can be run locally using uvx or via a Docker container.

Using uvx:

uvx semgrep-mcp # see --help for more options

Using Docker:

docker run -i --rm ghcr.io/semgrep/mcp -t stdio

Note: This repository is deprecated. Further updates will be made via the official semgrep binary in the main semgrep repository.

The semgrep-mcp package is available on PyPI and can be installed using standard Python package managers like pipx, uv, or poetry. To install it globally using pipx:

$ pipx install semgrep-mcp

Add the following configuration to your claude_desktop_config.json file.

{
  "mcpServers": {
    "semgrep": {
      "command": "uvx",
      "args": ["semgrep-mcp"]
    }
  }
}

Add the following block to your ~/.codeium/windsurf/mcp_config.json file.

{
  "mcpServers": {
    "semgrep": {
      "command": "uvx",
      "args": ["semgrep-mcp"]
    }
  }
}

To use the server in VS Code, add the configuration to your User Settings (JSON) or a workspace-specific .vscode/mcp.json file.

Using uvx:

{
  "mcp": {
    "servers": {
      "semgrep": {
        "command": "uvx",
        "args": ["semgrep-mcp"]
      }
    }
  }
}

Using Docker:

{
  "mcp": {
    "servers": {
      "semgrep": {
        "command": "docker",
        "args": [
          "run",
          "-i",
          "--rm",
          "ghcr.io/semgrep/mcp",
          "-t",
          "stdio"
        ]
      }
    }
  }
}

To use the Semgrep AppSec Platform features, you must provide an API token generated from your Semgrep organization settings. Use the environment variable SEMGREP_APP_TOKEN.

Methods to provide the token:

• CLI: export SEMGREP_APP_TOKEN=<token>
• Docker: docker run -e SEMGREP_APP_TOKEN=<token> ...
• MCP Config JSON:

  "env": {
    "SEMGREP_APP_TOKEN": "<token>"
  }