CodeRAG MCP server

CodeRAG is an enterprise code intelligence platform that transforms complex software projects into searchable knowledge graphs. By mapping code structures, dependencies, and relationships, it enables AI development tools to provide contextually accurate assistance for enterprise-scale codebases through advanced graph-based code analysis.

Installation & Setup

To get started with CodeRAG, follow these steps to install and configure the platform:

Prerequisites

• Neo4J database instance
• Access to your code repositories (local or remote)
• Supported programming languages: TypeScript, JavaScript, Java, or Python

Installation

1. Install CodeRAG using npm:

npm install -g coderag

2. Configure your Neo4J database connection:

coderag config --db-url neo4j://localhost:7687 --db-user neo4j --db-password yourpassword

3. Verify your installation:

coderag --version

Basic Usage

Analyzing a Local Project

To analyze a local codebase:

coderag scan --path /path/to/your/project

Analyzing a Remote Repository

For GitHub, GitLab, or Bitbucket repositories:

coderag scan --repo https://github.com/username/repository

For private repositories, add authentication:

coderag scan --repo https://github.com/username/repository --auth-token YOUR_ACCESS_TOKEN

Advanced Features

Multi-Project Management

For enterprise environments with multiple codebases:

coderag project create --name "Project Name"
coderag project add --name "Project Name" --repo https://github.com/username/repository
coderag project scan --name "Project Name"

Semantic Code Search

Search code by functionality using natural language:

coderag search "Find all methods that handle API authentication"

Quality Assessment

Generate code quality metrics:

coderag metrics --project "Project Name"

Integration with AI Tools

CodeRAG integrates with various AI coding assistants:

Claude Code Integration

coderag integrate --tool claude --api-key YOUR_ANTHROPIC_API_KEY

GitHub Copilot Integration

coderag integrate --tool copilot

Cursor Integration

coderag integrate --tool cursor --path /path/to/cursor/config

Available Reports

Generate detailed reports about your codebase:

# Generate architectural overview
coderag report architecture --project "Project Name"

# Generate technical debt report
coderag report debt --project "Project Name"

# Generate dependency graph
coderag report dependencies --project "Project Name"

Troubleshooting

Common Issues

• Connection Failed: Verify Neo4J credentials and ensure the database is running
• Analysis Timeout: For large repositories, increase timeout with --timeout 300
• Language Detection Issues: Specify language explicitly with --language java

Increasing Memory Allocation

For large codebases:

coderag scan --max-memory 8g --path /path/to/large/project

Enterprise Support

For additional support options and enterprise features, use the built-in help command:

coderag help

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "coderag" '{"command":"npx","args":["-y","coderag"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "coderag": {
            "command": "npx",
            "args": [
                "-y",
                "coderag"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "coderag": {
            "command": "npx",
            "args": [
                "-y",
                "coderag"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect