Mcp Server Semgrep — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Server Semgrep (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
MCP Server Semgrep Logo This project was initially inspired by robustness of Semgrep tool, The Replit Team and their Agent V2, as well as the implementation by stefanskiasan/semgrep-mcp-server, but has evolved with significant architectural changes for enhanced and easier installation and maintenance.
MCP Server Semgrep is a Model Context Protocol compliant server that integrates the powerful Semgrep static analysis tool with AI assistants like Anthropic Claude. It enables advanced code analysis, security vulnerability detection, and code quality improvements directly through a conversational interface.
Semgrep MCP Server provides the following tools:
The easiest way to install and use MCP Server Semgrep is through Smithery.ai:
This is the recommended method for Claude Desktop and other MCP clients as it handles all dependencies and configuration automatically.
# Using npm
npm install -g mcp-server-semgrep
# Using pnpm
pnpm add -g mcp-server-semgrep
# Using yarn
yarn global add mcp-server-semgrepThe package is also available on other registries:
# Using npm
npm install -g git+https://github.com/VetCoders/mcp-server-semgrep.git
# Using pnpm
pnpm add -g git+https://github.com/VetCoders/mcp-server-semgrep.git
# Using yarn
yarn global add git+https://github.com/VetCoders/mcp-server-semgrep.gitgit clone https://github.com/VetCoders/mcp-server-semgrep.git
cd mcp-server-semgrep# Using pnpm (recommended)
pnpm install
# Using npm
npm install
# Using yarn
yarn install# Using pnpm
pnpm run build
# Using npm
npm run build
# Using yarn
yarn buildNote: The installation process will automatically check for Semgrep availability. If Semgrep is not found, you'll receive instructions on how to install it.
This server only reads and writes files inside explicitly allowed workspace roots.
process.cwd()).MCP_SERVER_SEMGREP_ALLOWED_ROOTS to one or more absolute directories.: on macOS/Linux, ; on Windows.This server does not implement its own Semgrep account handling. It shells out to the installed semgrep CLI and relies on Semgrep's normal authentication behavior.
semgrep login session from the current OS account.SEMGREP_APP_TOKEN for deterministic behavior.SEMGREP_APP_TOKEN is still the safest option when you need portable configuration across machines or runners.Semgrep can be installed in several ways:
# Using pnpm
pnpm add -g semgrep
# Using npm
npm install -g semgrep
# Using yarn
yarn global add semgrep pip install semgrep brew install semgrep sudo apt-get install semgrep
# or
curl -sSL https://install.semgrep.dev | sh pip install semgrepThere are two ways to integrate MCP Server Semgrep with Claude Desktop:
claude_desktop_config.json) and add this to your servers section.For local launches started under a user account that is already authenticated with semgrep login, the Semgrep CLI may be able to reuse that login. For desktop-managed or shared environments, we still recommend setting SEMGREP_APP_TOKEN explicitly:
{
"mcpServers": {
"semgrep": {
"command": "node",
"args": [
"/your_path/mcp-server-semgrep/build/index.js"
],
"env": {
"SEMGREP_APP_TOKEN": "your_semgrep_app_token",
"MCP_SERVER_SEMGREP_ALLOWED_ROOTS": "/Users/you/projects"
}
}
}
}If you want to scan more than one workspace, set MCP_SERVER_SEMGREP_ALLOWED_ROOTS to a platform-delimited list of absolute paths.
Could you scan my source code in the /projects/my-application directory for potential security issues? That directory is already included in MCP_SERVER_SEMGREP_ALLOWED_ROOTS.Analyze the z-index values in the project's CSS files and identify inconsistencies and potential layer conflicts.Create a Semgrep rule that detects improper use of input sanitization functions.Show me only scan results related to SQL injection vulnerabilities.Find all "magic numbers" in the code and suggest replacing them with named constants.You can create custom rules for your project's specific needs. Here are examples of rules you can create:
rules:
- id: inconsistent-z-index
pattern: z-index: $Z
message: "Z-index $Z may not comply with the project's layering system"
languages: [css, scss]
severity: WARNINGrules:
- id: deprecated-import
pattern: import $X from 'old-library'
message: "You're using a deprecated library. Consider using 'new-library'"
languages: [javascript, typescript]
severity: WARNINGpnpm test├── src/
│ └── index.ts # Main entry point and all handler implementations
├── scripts/
│ └── check-semgrep.js # Semgrep detection and installation helper
├── build/ # Compiled JavaScript (after build)
└── tests/ # Unit testsDetailed information on using the tool can be found in:
This project is licensed under the MIT License - see the LICENSE file for details.
bash a half year agoThe journey from CLI novice to MCP tool developer
🤖 Developed with the ultimate help of Claude Code and MCP Tools
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.