home / mcp / codechecker mcp server

CodeChecker MCP Server

Cursor code-checker MCP

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "jacklandis29-codechecker-mcp": {
      "url": "http://127.0.0.1:8000/sse",
      "headers": {
        "OPENAI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

CodeChecker MCP is a code review assistant that runs as a local MCP server and uses OpenAI models to analyze code and offer actionable suggestions inside Cursor IDE. It helps you get real-time insights during review sessions and integrates smoothly with your development workflow.

How to use

Start the MCP server locally and connect Cursor IDE to it to receive real-time code review guidance. You will run the server on a port you choose, then configure Cursor to point at the server’s SSE endpoint. Once connected, select code in Cursor and provide context for the review to receive detailed analysis and improvement suggestions.

How to install

# Prerequisites
# - Python 3.10 or higher
# - Cursor IDE
# - OpenAI API key

# 1. Clone the project
git clone https://github.com/jacklandis29/codechecker-mcp.git
cd codechecker-mcp

# 2. Create and activate a virtual environment
python -m venv venv
# On macOS/Linux
source venv/bin/activate
# On Windows
venv\Scripts\activate

# 3. Install dependencies
pip install -e .

# 4. Configure your OpenAI API key
# Create a .env file in the project root
OPENAI_API_KEY=your_api_key_here

5. Start the MCP server using SSE transport on a chosen port.

Configuration

The server can be started with SSE transport and a specific port. To connect Cursor IDE, configure the MCP endpoint to the SSE URL exposed by the server.

{
  "mcp": {
    "endpoint": "http://127.0.0.1:8000/sse",
    "enabled": true
  }
}

Available tools

code_review

Performs real-time code analysis and provides targeted improvement suggestions using OpenAI GPT models.