mcpField
C
Cursor MCP (Model Context Protocol)

Cursor MCP (Model Context Protocol)

github.com/sirvenisIDEs & Editors7Updated 84w ago
Repository

About Cursor MCP (Model Context Protocol)

Chrome extension that connects the browser and Cursor IDE via MCP, enabling context sharing. Helps developers access browser data directly in the IDE.

Key features

  1. 01Capture console logs and errors
  2. 02Track network requests and responses
  3. 03Take screenshots and select DOM elements
  4. 04Register commands with Cursor IDE
  5. 05Configure logging settings

Use cases

  1. 01Debug browser errors from the IDE
  2. 02Analyze network activity for troubleshooting
  3. 03Capture screenshots and inspect page elements

MCP support

As an MCP client, the extension exposes browser data to Cursor IDE via MCP, including console logs, network requests, screenshots, and DOM elements.

Details

From the project README

Cursor MCP (Model Context Protocol)

A Chrome extension that integrates with Cursor IDE through the Model Context Protocol (MCP), allowing for enhanced context sharing between the browser and the IDE.

Features

  • Capture console logs and errors
  • Track network requests and responses
  • Take screenshots
  • Get selected DOM elements
  • Register commands with Cursor IDE
  • Configure logging settings

Installation

Browser Extension
  1. Clone this repository
  2. Open Chrome and navigate to chrome://extensions/
  3. Enable Developer Mode (toggle in the top right)
  4. Click "Load unpacked" and select the cloned repository folder
  5. The extension should now be installed and visible in your browser toolbar
Adding to Cursor Settings
  1. Open Cursor IDE
  2. Go to Settings (gear icon in the bottom left corner)
  3. Navigate to the "Extensions" or "MCPs" section
  4. Click "Add MCP"
  5. Enter the MCP information and click "Add"

Usage

You can use the MCP directly from Cursor IDE after adding it to your settings:

`javascript // Get console logs const logs = await mcp.getConsoleLogs();

// Take a screenshot const screenshot = await mcp.takeScreenshot();

// Get all context const context = await mcp.getAllContext(); `

Configuration

The MCP can be configured with the following options:

  • Log limit: Maximum number of logs to keep
  • Query limit: Maximum size of query to process
  • Show request headers: Whether to include request headers in network logs
  • Show response headers: Whether to include response headers in network logs

Development

To contribute to this project, follow these steps:

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

Documentation

For more detailed information, see the following documentation:

License

MIT

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.