### Install and Get Help for Semgrep MCP

Source: https://github.com/semgrep/mcp/blob/main/README.md

Install the package using pipx and view the command-line help for available options.

```bash
$ pipx install semgrep-mcp
$ semgrep-mcp --help
```

--------------------------------

### Run Development Server

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Starts the MCP server in development mode using `uv`. This mode is optimized for local development and debugging.

```bash
uv run mcp dev ./src/semgrep_mcp/server.py
```

--------------------------------

### Install Semgrep CLI

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Installs the Semgrep CLI tool. Ensure Python 3.13+ is installed and the repository is cloned.

```bash
pip install semgrep
```

--------------------------------

### OpenAI Agents SDK MCPServerStdio Initialization

Source: https://github.com/semgrep/mcp/blob/main/README.md

Example of initializing MCPServerStdio with Semgrep MCP server parameters using the OpenAI Agents SDK.

```python
async with MCPServerStdio(
    params={
        "command": "uvx",
        "args": ["semgrep-mcp"],
    }
) as server:
    tools = await server.list_tools()
```

--------------------------------

### Install semgrep-mcp Helm Chart

Source: https://github.com/semgrep/mcp/blob/main/chart/semgrep-mcp/README.md

Use this command to install the semgrep-mcp Helm chart in your cluster.

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

--------------------------------

### Run MCP Server (STDIO Mode - CLI)

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Starts the MCP server in STDIO mode using the CLI. This is useful for integrating with other tools that communicate via standard input/output.

```bash
uv run mcp run ./src/semgrep_mcp/server.py -t stdio
```

--------------------------------

### Configure SEMGREP_APP_TOKEN in values.yaml

Source: https://github.com/semgrep/mcp/blob/main/chart/semgrep-mcp/README.md

Example of how to set the SEMGREP_APP_TOKEN environment variable in your values.yaml file for the semgrep-mcp Helm chart.

```yaml
env:
  - name: SEMGREP_APP_TOKEN
    value: "your-token-here"
```

--------------------------------

### Cursor MCP Server Configuration

Source: https://github.com/semgrep/mcp/blob/main/README.md

Example mcp.json configuration for Cursor IDE to connect to a Semgrep MCP server. Requires a Semgrep App Token.

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

```

--------------------------------

### Run Semgrep MCP with Streamable HTTP Transport

Source: https://github.com/semgrep/mcp/blob/main/README.md

Start the semgrep-mcp server using the streamable-http transport. This is the recommended transport for client connections.

```bash
semgrep-mcp -t streamable-http
```

--------------------------------

### Build MCP Docker Image

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Builds the Docker image for the MCP server. Requires Docker to be installed and Semgrep API token configured.

```bash
make docker
```

--------------------------------

### Run MCP Server (SSE Mode - CLI)

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Starts the MCP server in SSE (Server-Sent Events) mode using the CLI. This mode is suitable for real-time updates and notifications.

```bash
uv run mcp run ./src/semgrep_mcp/server.py -t sse
```

--------------------------------

### Custom Python SSE Client for MCP

Source: https://github.com/semgrep/mcp/blob/main/README.md

An example of a custom Python SSE client that connects to an MCP server and calls a tool. Ensure the server is running and accessible at the specified URL.

```python
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)
```

--------------------------------

### Cursor IDE Rule for Semgrep

Source: https://github.com/semgrep/mcp/blob/main/README.md

An example instruction to add to Cursor IDE's .cursor/rules to automatically scan generated code with Semgrep for security vulnerabilities.

```text
Always scan code generated using Semgrep for security vulnerabilities
```

--------------------------------

### Increase Inspector Server Timeout

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Example URL to access the inspector server with an increased timeout parameter. Adjust the `timeout` value as needed.

```http
http://localhost:6274/?timeout=300000
```

--------------------------------

### Run Semgrep MCP CLI with uvx

Source: https://github.com/semgrep/mcp/blob/main/README.md

Execute the Semgrep MCP package as a command-line tool using uvx. Use --help for more options.

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

--------------------------------

### Workspace .vscode/mcp.json Configuration

Source: https://github.com/semgrep/mcp/blob/main/README.md

Optionally, configure the Semgrep MCP server by adding this JSON block to a `.vscode/mcp.json` file in your workspace.

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

--------------------------------

### Prompts

Source: https://github.com/semgrep/mcp/blob/main/README.md

Reusable prompts to standardize common LLM interactions.

```APIDOC
## Prompts

Reusable prompts to standardize common LLM interactions.

- `write_custom_semgrep_rule`: Return a prompt to help write a Semgrep rule
```

--------------------------------

### Execute MCP Server Script

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Makes the server script executable and displays its help message. Useful for understanding available command-line arguments.

```bash
chmod +x ./src/semgrep_mcp/server.py
./src/semgrep_mcp/server.py --help
```

--------------------------------

### Tools

Source: https://github.com/semgrep/mcp/blob/main/README.md

Enable LLMs to perform actions, make deterministic computations, and interact with external services.

```APIDOC
## Tools

Enable LLMs to perform actions, make deterministic computations, and interact with external services.

### Scan Code

- `security_check`: Scan code for security vulnerabilities
- `semgrep_scan`: Scan code files for security vulnerabilities with a given config string
- `semgrep_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 supports
- `semgrep_rule_schema`: Fetches the latest semgrep rule JSON Schema
```

--------------------------------

### Cursor MCP Server Configuration (Streamable HTTP)

Source: https://github.com/semgrep/mcp/blob/main/README.md

Configuration for Cursor IDE to connect to the Semgrep hosted server using streamable HTTP. This is an experimental server.

```json
{
  "mcpServers": {
    "semgrep": {
      "type": "streamable-http",
      "url": "https://mcp.semgrep.ai/mcp"
    }
  }
}

```

--------------------------------

### Run MCP Server (STDIO Mode - Docker)

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Runs the MCP server in STDIO mode using Docker. This provides an isolated environment for the server.

```bash
docker run -i --rm semgrep-mcp -t stdio
```

--------------------------------

### Run Semgrep MCP with Docker

Source: https://github.com/semgrep/mcp/blob/main/README.md

Execute the Semgrep MCP package as a Docker container. Use the -t stdio flag for standard input/output.

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

--------------------------------

### Docker MCP Server Configuration

Source: https://github.com/semgrep/mcp/blob/main/README.md

Configure the Semgrep MCP server to run using Docker. This JSON block specifies the Docker image and command to execute.

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

--------------------------------

### Resources

Source: https://github.com/semgrep/mcp/blob/main/README.md

Expose data and content to LLMs.

```APIDOC
## Resources

Expose data and content to LLMs

- `semgrep://rule/schema`: Specification of the Semgrep rule YAML syntax using JSON schema
- `semgrep://rule/{rule_id}/yaml`: Full Semgrep rule in YAML format from the Semgrep registry
```

--------------------------------

### Run Semgrep MCP with Stdio Transport

Source: https://github.com/semgrep/mcp/blob/main/README.md

Execute the semgrep-mcp server using the stdio transport. This is the default mode and suitable for local integrations. The tool may appear to hang as it reads from stdin and writes to stdout.

```bash
semgrep-mcp
```

--------------------------------

### Configure Semgrep MCP for Cursor IDE

Source: https://github.com/semgrep/mcp/blob/main/README.md

Add this JSON configuration to your Cursor IDE's mcp.json file to integrate with semgrep-mcp.

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

--------------------------------

### Configure Semgrep AppSec Platform Token

Source: https://github.com/semgrep/mcp/blob/main/README.md

Set the SEMGREP_APP_TOKEN environment variable for connecting to Semgrep AppSec Platform. This can be done via CLI, Docker, or MCP config JSON.

```bash
export SEMGREP_APP_TOKEN=<token>
```

```bash
docker run -e SEMGREP_APP_TOKEN=<token>
```

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

--------------------------------

### Push Git Tag

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Pushes a Git tag to the origin repository. Replace `vX.Y.Z` with the actual version tag.

```bash
git push origin vX.Y.Z
```

--------------------------------

### Run MCP Server (SSE Mode - Docker)

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Runs the MCP server in SSE mode using Docker, exposing port 8000 for communication. This is suitable for applications requiring real-time analysis.

```bash
docker run -p 8000:8000 semgrep-mcp
```

--------------------------------

### Run Semgrep MCP Docker with Streamable HTTP Transport

Source: https://github.com/semgrep/mcp/blob/main/README.md

Deploy the semgrep-mcp server using Docker with the streamable-http transport. The server will listen on port 8000.

```bash
docker run -p 8000:0000 ghcr.io/semgrep/mcp
```

--------------------------------

### Run Semgrep MCP Docker with SSE Transport

Source: https://github.com/semgrep/mcp/blob/main/README.md

Deploy the semgrep-mcp server using Docker with the SSE transport. The server will listen on port 8000.

```bash
docker run -p 8000:0000 ghcr.io/semgrep/mcp -t sse
```

--------------------------------

### Bump Version Script

Source: https://github.com/semgrep/mcp/blob/main/CONTRIBUTING.md

Executes a script to bump the project version. It accepts 'patch', 'minor', or 'major' as an argument, defaulting to 'minor'.

```bash
# takes one argument {patch, minor, major} with 'minor' as the default argument
uv run python ./scripts/bump_version.py 
```

--------------------------------

### VS Code User Settings JSON Configuration

Source: https://github.com/semgrep/mcp/blob/main/README.md

Add this JSON block to your VS Code User Settings (JSON) file for manual configuration of the Semgrep MCP server.

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

--------------------------------

### Run Semgrep MCP with SSE Transport

Source: https://github.com/semgrep/mcp/blob/main/README.md

Execute the semgrep-mcp server using the SSE (Server-Sent Events) transport. This is a legacy transport protocol.

```bash
semgrep-mcp -t sse
```

--------------------------------

### Claude Code MCP Add Command

Source: https://github.com/semgrep/mcp/blob/main/README.md

Use this bash command to add the Semgrep MCP server to Claude Code.

```bash
claude mcp add semgrep uvx semgrep-mcp
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.