Cursor IDE

Cursor is an AI-powered IDE that supports servers. This guide will help you integrate your Arcade with Cursor for enhanced development capabilities.

Prerequisites

Cursor IDE installed
Python 3.10+ installed
arcade-mcp package installed (pip install arcade-mcp)

Configuration

Cursor reads server configurations from its settings. You can configure through:

Cursor Settings UI
Configuration file
Workspace settings

Basic setup

Method 1: Settings UI

Open Cursor Settings (Cmd/Ctrl + Shift + J)
Search for “” or “Model Protocol”
Add a new server configuration:
- Name: arcade-tools
- Command: python -m arcade_mcp stdio
- Working Directory: /path/to/your/project

Method 2: Configuration file

Add to your Cursor configuration:

JSON


{
  "mcp.servers": {
    "arcade-tools": {
      "command": "python",
      "args": ["-m", "arcade_mcp", "stdio"],
      "cwd": "${workspaceFolder}",
      "env": {
        "PYTHONPATH": "${workspaceFolder}"
      }
    }
  }
}

Method 3: Workspace settings

Create .cursor/settings.json in your workspace:

JSON


{
  "mcp.servers": {
    "project-tools": {
      "command": "python",
      "args": ["-m", "arcade_mcp", "stdio", "--debug"],
      "cwd": "${workspaceFolder}",
      "env": {
        "ARCADE_API_KEY": "${env:ARCADE_API_KEY}"
      }
    }
  }
}

Development workflow

Hot reload setup

For active development with automatic reload:

JSON


{
  "mcp.servers": {
    "dev-tools": {
      "command": "python",
      "args": ["-m", "arcade_mcp", "--reload", "--debug"],
      "cwd": "${workspaceFolder}",
      "env": {
        "PYTHONPATH": "${workspaceFolder}"
      }
    }
  }
}

Virtual environment

Use a -specific virtual environment:

JSON


{
  "mcp.servers": {
    "project-tools": {
      "command": "${workspaceFolder}/venv/bin/python",
      "args": ["-m", "arcade_mcp", "stdio"],
      "cwd": "${workspaceFolder}"
    }
  }
}

Multiple tool sets

Configure different sets for different purposes:

JSON


{
  "mcp.servers": {
    "github-tools": {
      "command": "python",
      "args": ["-m", "arcade_mcp", "stdio", "--tool-package", "github"],
      "env": {
        "GITHUB_TOKEN": "${env:GITHUB_TOKEN}"
      }
    },
    "database-tools": {
      "command": "python",
      "args": ["-m", "arcade_mcp", "stdio"],
      "cwd": "${workspaceFolder}/db_tools",
      "env": {
        "DATABASE_URL": "${env:DATABASE_URL}"
      }
    },
    "api-tools": {
      "command": "python",
      "args": ["-m", "arcade_mcp", "stdio"],
      "cwd": "${workspaceFolder}/api_tools"
    }
  }
}

Integration features

Inline tool usage

Use directly in your code comments:

Python


# @mcp use arcade-tools.greet name="World"
# Result will appear here
 
def process_data(data):
    # @mcp use database-tools.query sql="SELECT * FROM users"
    pass

Tool discovery

View available in Cursor:

Open Command Palette (Cmd/Ctrl + Shift + P)
Type “: List ”
Select your server to see available

Tool documentation

Access documentation:

Hover over usage in code
Use Cmd/Ctrl + Click on names
View in the panel

Advanced configuration

Environment-specific settings

Use different configurations per environment:

JSON


{
  "mcp.servers": {
    "tools-dev": {
      "command": "python",
      "args": ["-m", "arcade_mcp", "stdio", "--env-file", ".env.dev"],
      "cwd": "${workspaceFolder}",
      "when": "${config:environment} == 'development'"
    },
    "tools-prod": {
      "command": "python",
      "args": ["-m", "arcade_mcp", "stdio", "--env-file", ".env.prod"],
      "cwd": "${workspaceFolder}",
      "when": "${config:environment} == 'production'"
    }
  }
}

Task integration

Create tasks for server management:

JSON


{
  "version": "2.0.0",
  "tasks": [
    {
      "label": "Start MCP Server",
      "type": "shell",
      "command": "python -m arcade_mcp --reload --debug",
      "problemMatcher": [],
      "isBackground": true
    },
    {
      "label": "Test Tools",
      "type": "shell",
      "command": "python -m arcade_mcp --tool-package ${input:package} --debug",
      "problemMatcher": []
    }
  ],
  "inputs": [
    {
      "id": "package",
      "type": "promptString",
      "description": "Tool package name"
    }
  ]
}

Debugging tools

Debug your with Cursor’s debugger:

JSON


{
  "version": "0.2.0",
  "configurations": [
    {
      "name": "Debug MCP Tools",
      "type": "python",
      "request": "launch",
      "module": "arcade_mcp",
      "args": ["--debug", "--reload"],
      "cwd": "${workspaceFolder}",
      "env": {
        "PYTHONPATH": "${workspaceFolder}"
      }
    }
  ]
}

Best practices

Project structure

Organize your effectively:

PLAINTEXT


my-project/
├── .cursor/
│   └── settings.json    # Cursor-specific settings
├── .env                 # Environment variables
├── .env.example         # Example environment file
├── tools/
│   ├── __init__.py
│   ├── data_tools.py    # Data processing tools
│   ├── api_tools.py     # API interaction tools
│   └── utils.py         # Utility tools
├── requirements.txt
└── README.md

Tool development tips

Use type hints: Enable better IDE support

Python


from typing import Annotated
 
@tool
def process(
    data: Annotated[str, "Input data to process"],
    format: Annotated[str, "Output format"] = "json"
) -> Annotated[dict, "Processed data"]:
    """Process data in the specified format."""
    pass

Provide clear descriptions: Help Cursor understand usage
Handle errors gracefully: Return helpful error messages
Use logging: Enable debug mode for troubleshooting
Test incrementally: Use Cursor’s integrated terminal

Performance optimization

Lazy loading: Import heavy dependencies inside
Cache results: Use caching for expensive operations
Async support: Use async for I/O operations
Resource management: Clean up resources properly

Troubleshooting

Common issues

Server not starting

Check Python path and virtual environment
Verify arcade-mcp installation
Enable debug logging to see errors
Check for import errors in files

Permission errors

Ensure proper file permissions
Check working directory access
Verify environment variable access

Connection issues

Restart Cursor after configuration changes
Check for conflicting servers
Verify stdio transport is working

Debugging steps

Enable debug mode in your configuration
Check Cursor’s output panel for logs
Test using the command line first
Use Cursor’s Developer for detailed logs

Example: Complete setup

Here’s a full example of setting up a Cursor workspace with :

Create workspace structure:

PLAINTEXT


my-workspace/
├── .cursor/
│   └── settings.json
├── .vscode/
│   └── tasks.json
├── tools/
│   └── my_tools.py
└── pyproject.toml

Configure .cursor/settings.json:

JSON


{
  "mcp.servers": {
    "workspace-tools": {
      "command": "python",
      "args": ["-m", "arcade_mcp", "stdio", "--debug"],
      "cwd": "${workspaceFolder}",
      "env": {
        "PYTHONPATH": "${workspaceFolder}"
      }
    }
  }
}

Create tools/my_tools.py:

Python


from arcade_mcp_server import tool
from typing import Annotated
import json
 
@tool
async def format_json(
    data: Annotated[str, "JSON string to format"]
) -> Annotated[str, "Formatted JSON"]:
    """Format JSON data with proper indentation."""
    parsed = json.loads(data)
    return json.dumps(parsed, indent=2)
 
@tool
def analyze_code(
    file_path: Annotated[str, "Path to analyze"]
) -> Annotated[dict, "Analysis results"]:
    """Analyze Python code quality."""
    # Implementation here
    pass

Restart Cursor and start using your !