Semgrep MCP Server
OfficialThe Semgrep MCP Server provides a Model Context Protocol (MCP) interface for static code analysis and security scanning using Semgrep. With this server, you can:
Start scans using code content (
start_scan_from_content), target files/directories (start_scan), or custom rulesMonitor scan status of ongoing scans (
get_scan_status)Retrieve scan results from completed scans (
get_scan_results)Run direct scans to get findings in JSON format (
semgrep_scan)Get supported languages that Semgrep can analyze
Configure scans with specific rules or 'auto' mode
Obtain Abstract Syntax Trees (AST) of code
Access resources like rule schemas and registry rules
Generate prompts to assist in writing custom Semgrep rules
These capabilities enable integration with IDEs, LLMs, and other tools for effective security vulnerability detection.
Provides instructions for running the MCP server in a containerized environment using Docker.
Includes integration references for accessing repositories and issue tracking functionality.
Provides a Python client interface for interacting with the MCP server and executing Semgrep scans programmatically.
References community access through Slack for support and collaboration with other users.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Semgrep MCP Server scan this Python file for security vulnerabilities"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
⚠️ The Semgrep MCP server has been moved from a standalone repo to the main semgrep repository! ⚠️
This repository has been deprecated, and further updates to the Semgrep MCP server will be made via the official semgrep binary.
Semgrep MCP Server
A Model Context Protocol (MCP) server for using Semgrep to scan code for security vulnerabilities. Secure your vibe coding! 😅
Model Context Protocol (MCP) is a standardized API for LLMs, Agents, and IDEs like Cursor, VS Code, Windsurf, or anything that supports MCP, to get specialized help, get context, and harness the power of tools. Semgrep is a fast, deterministic static analysis tool that semantically understands many languages and comes with over 5,000 rules. 🛠️
This beta project is under active development. We would love your feedback, bug reports, feature requests, and code. Join the#mcp community Slack channel!
Related MCP server: MCP Server Semgrep
Contents
Getting started
Run the Python package as a CLI command using uv:
uvx semgrep-mcp # see --help for more optionsOr, run as a Docker container:
docker run -i --rm ghcr.io/semgrep/mcp -t stdioCursor
Example mcp.json
{
"mcpServers": {
"semgrep": {
"command": "uvx",
"args": ["semgrep-mcp"],
"env": {
"SEMGREP_APP_TOKEN": "<token>"
}
}
}
}
Add an instruction to your .cursor/rules to use automatically:
Always scan code generated using Semgrep for security vulnerabilitiesChatGPT
Go to the Connector Settings page (direct link)
Name the connection
SemgrepSet MCP Server URL to
https://mcp.semgrep.ai/sseSet Authentication to
No authenticationCheck the I trust this application checkbox
Click Create
See more details at the official docs.
Hosted Server
mcp.semgrep.ai is an experimental server that may break unexpectedly. It will rapidly gain new functionality.🚀
Cursor
Cmd + Shift + J to open Cursor Settings
Select MCP Tools
Click New MCP Server.
{
"mcpServers": {
"semgrep": {
"type": "streamable-http",
"url": "https://mcp.semgrep.ai/mcp"
}
}
}Demo
API
Tools
Enable LLMs to perform actions, make deterministic computations, and interact with external services.
Scan Code
security_check: Scan code for security vulnerabilitiessemgrep_scan: Scan code files for security vulnerabilities with a given config stringsemgrep_scan_with_custom_rule: Scan code files using a custom Semgrep rule
Understand Code
get_abstract_syntax_tree: Output the Abstract Syntax Tree (AST) of code
Cloud Platform (login and Semgrep token required)
semgrep_findings: Fetch Semgrep findings from the Semgrep AppSec Platform API
Meta
supported_languages: Return the list of languages Semgrep supportssemgrep_rule_schema: Fetches the latest semgrep rule JSON Schema
Prompts
Reusable prompts to standardize common LLM interactions.
write_custom_semgrep_rule: Return a prompt to help write a Semgrep rule
Resources
Expose data and content to LLMs
semgrep://rule/schema: Specification of the Semgrep rule YAML syntax using JSON schemasemgrep://rule/{rule_id}/yaml: Full Semgrep rule in YAML format from the Semgrep registry
Usage
This Python package is published to PyPI as semgrep-mcp and can be installed and run with pip, pipx, uv, poetry, or any Python package manager.
$ pipx install semgrep-mcp
$ semgrep-mcp --help
Usage: semgrep-mcp [OPTIONS]
Entry point for the MCP server
Supports both stdio and sse transports. For stdio, it will read from stdin
and write to stdout. For sse, it will start an HTTP server on port 8000.
Options:
-v, --version Show version and exit.
-t, --transport [stdio|sse] Transport protocol to use (stdio or sse)
-h, --help Show this message and exit.Standard Input/Output (stdio)
The stdio transport enables communication through standard input and output streams. This is particularly useful for local integrations and command-line tools. See the spec for more details.
Python
semgrep-mcpBy default, the Python package will run in stdio mode. Because it's using the standard input and output streams, it will look like the tool is hanging without any output, but this is expected.
Docker
This server is published to Github's Container Registry (ghcr.io/semgrep/mcp)
docker run -i --rm ghcr.io/semgrep/mcp -t stdioBy default, the Docker container is in SSE mode, so you will have to include -t stdio after the image name and run with -i to run in interactive mode.
Streamable HTTP
Streamable HTTP enables streaming responses over JSON RPC via HTTP POST requests. See the spec for more details.
By default, the server listens on 127.0.0.1:8000/mcp for client connections. To change any of this, set FASTMCP_* environment variables. The server must be running for clients to connect to it.
Python
semgrep-mcp -t streamable-httpBy default, the Python package will run in stdio mode, so you will have to include -t streamable-http.
Docker
docker run -p 8000:0000 ghcr.io/semgrep/mcpServer-sent events (SSE)
The MCP communiity considers this a legacy transport portcol and is really intended for backwards compatibility.Streamable HTTP is the recommended replacement.
SSE transport enables server-to-client streaming with Server-Send Events for client-to-server and server-to-client communication. See the spec for more details.
By default, the server listens on 127.0.0.1:8000/sse for client connections. To change any of this, set FASTMCP_* environment variables. The server must be running for clients to connect to it.
Python
semgrep-mcp -t sseBy default, the Python package will run in stdio mode, so you will have to include -t sse.
Docker
docker run -p 8000:0000 ghcr.io/semgrep/mcp -t sseSemgrep AppSec Platform
Optionally, to connect to Semgrep AppSec Platform:
Login or sign up
Generate a token from Settings
Add the token to your environment variables:
CLI (
export SEMGREP_APP_TOKEN=<token>)Docker (
docker run -e SEMGREP_APP_TOKEN=<token>)MCP config JSON
"env": {
"SEMGREP_APP_TOKEN": "<token>"
}Pleasereach out for support if needed. ☎️
Integrations
Cursor IDE
Add the following JSON block to your ~/.cursor/mcp.json global or .cursor/mcp.json project-specific configuration file:
{
"mcpServers": {
"semgrep": {
"command": "uvx",
"args": ["semgrep-mcp"]
}
}
}
See cursor docs for more info.
VS Code / Copilot
Click the install buttons at the top of this README for the quickest installation.
Manual Configuration
Add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open User Settings (JSON).
{
"mcp": {
"servers": {
"semgrep": {
"command": "uvx",
"args": ["semgrep-mcp"]
}
}
}
}Optionally, you can add it to a file called .vscode/mcp.json in your workspace:
{
"servers": {
"semgrep": {
"command": "uvx",
"args": ["semgrep-mcp"]
}
}
}Using Docker
{
"mcp": {
"servers": {
"semgrep": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/semgrep/mcp",
"-t",
"stdio"
]
}
}
}
}See VS Code docs for more info.
Windsurf
Add the following JSON block to your ~/.codeium/windsurf/mcp_config.json file:
{
"mcpServers": {
"semgrep": {
"command": "uvx",
"args": ["semgrep-mcp"]
}
}
}See Windsurf docs for more info.
Claude Desktop
Here is a short video showing Claude Desktop using this server to write a custom rule.
Add the following JSON block to your claude_desktop_config.json file:
{
"mcpServers": {
"semgrep": {
"command": "uvx",
"args": ["semgrep-mcp"]
}
}
}See Anthropic docs for more info.
Claude Code
claude mcp add semgrep uvx semgrep-mcpSee Claude Code docs for more info.
OpenAI
See the offical docs:
Agents SDK
async with MCPServerStdio(
params={
"command": "uvx",
"args": ["semgrep-mcp"],
}
) as server:
tools = await server.list_tools()See OpenAI Agents SDK docs for more info.
Custom clients
Example Python SSE client
See a full example in examples/sse_client.py
from mcp.client.session import ClientSession
from mcp.client.sse import sse_client
async def main():
async with sse_client("http://localhost:8000/sse") as (read_stream, write_stream):
async with ClientSession(read_stream, write_stream) as session:
await session.initialize()
results = await session.call_tool(
"semgrep_scan",
{
"code_files": [
{
"path": "hello_world.py",
"content": "def hello(): print('Hello, World!')",
}
]
},
)
print(results)Some client libraries want theURL: http://localhost:8000/sse
and others only want the HOST: localhost:8000.
Try out the URL in a web browser to confirm the server is running, and there are no network issues.
See official SDK docs for more info.
Contributing, community, and running from source
We love your feedback, bug reports, feature requests, and code. Join the#mcp community Slack channel!
See CONTRIBUTING.md for more info and details on how to run from the MCP server from source code.
Similar tools 🔍
semgrep-vscode - Official VS Code extension
semgrep-intellij - IntelliJ plugin
Community projects 🌟
semgrep-rules - The official collection of Semgrep rules
mcp-server-semgrep - Original inspiration written by Szowesgad and stefanskiasan
MCP server registries
Made with ❤️ by the Semgrep Team
Available Tools
6 toolsget_scan_resultsC
Gets the results of a completed scan
Args: scan_id: Identifier for the scan
Returns: Dictionary with scan results
Inputs: scan_id (required).
get_scan_statusC
Gets the current status of a scan
Args: scan_id: Identifier for the scan
Returns: Dictionary with scan status information
Inputs: scan_id (required).
get_supported_languagesC
Returns a list of supported languages by Semgrep
Returns: List of supported languages
Inputs: no named parameters.
semgrep_scanA
Runs a Semgrep scan on provided code content and returns the findings in JSON format
Args: code_files: List of dictionaries with 'filename' and 'content' keys config: Semgrep configuration (e.g. "auto" or absolute path to rule file)
Returns: Dictionary with scan results in Semgrep JSON format
Inputs: code_files (required), config.
start_scanC
Starts a Semgrep scan with progress updates via notifications
Args: ctx: MCP context for sending notifications target_path: Absolute path to the file or directory to scan config: Semgrep configuration (e.g. "auto" or absolute path to rule file)
Returns: Dictionary with scan information
Inputs: target_path (required), config.
start_scan_from_contentC
Starts a Semgrep scan with code content provided directly
Args: ctx: MCP context for sending notifications code_files: List of dictionaries with 'filename' and 'content' keys config: Semgrep configuration (e.g. "auto" or absolute path to rule file)
Returns: Dictionary with scan information
Inputs: code_files (required), config.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
There is significant functional overlap between tools, particularly between semgrep_scan, start_scan, and start_scan_from_content, which all perform scanning operations with different interfaces. However, the descriptions clarify the distinctions between immediate vs. asynchronous scans and file-based vs. content-based inputs, helping agents differentiate them.
Tool names follow a consistent snake_case pattern with clear verb_noun structure (e.g., get_scan_results, start_scan). The only minor deviation is semgrep_scan, which uses the product name as a prefix rather than a verb, but this maintains readability and domain context.
With 6 tools, this server is well-scoped for code security scanning. It covers core operations like initiating scans, checking status, retrieving results, and getting language support, without being overly complex or sparse for the domain.
The toolset provides comprehensive coverage for scanning workflows, including both synchronous and asynchronous options, status tracking, and result retrieval. A minor gap is the lack of tools for managing scan configurations or rules beyond basic usage, but core operations are well-covered.
Maintenance
Related MCP Connectors
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Static MCP server scan: injection, secrets, tool poisoning. SARIF + rules catalog.
Zero-config MCP security scanner for AI-generated apps. 25K+ vulnerability patterns.
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables integration of Semgrep in development environments via the MCP protocol, supporting static code analysis, rule management, and scan result operations.2MIT
- AlicenseBqualityCmaintenanceA Model Context Protocol compliant server that integrates Semgrep static analysis tool with AI assistants like Anthropic Claude, enabling advanced code analysis, security vulnerability detection, and code quality improvements through a conversational interface.7250 npm29MIT
- AlicenseAqualityDmaintenanceA production-grade security auditing MCP server that wraps semgrep (SAST) and gitleaks (secret detection) to enable one-click code security scanning via MCP stdio protocol.1MIT
- AlicenseNot gradedqualityDmaintenanceSecurity scanning MCP server. Semgrep integration, SARIF parsing, baseline diffing, framework-aware ruleset selection, and automated finding triage.4 npm1MIT