This Model Context Protocol (MCP) server helps AI tools analyze and interact with your browser by capturing console logs, network requests, screenshots, and page elements. It creates a bridge between your browser activities and AI-powered applications.
Install the MCP server package:
npx @agentdeskai/[email protected]
Download the latest Chrome extension:
Run the local node server:
npx @agentdeskai/[email protected]
Note: Always specify the version (1.2.0) when using npx to ensure you get the latest release.
Open Chrome DevTools to start sending logs to your server
The MCP server enables AI tools to:
Enable "Allow Auto-Paste into Cursor" within the DevTools panel to automatically paste screenshots into Cursor. Make sure to focus on the Agent input field in Cursor for this to work.
The MCP server provides several audit tools that can be triggered with specific queries:
Checks page compliance with WCAG standards:
"Are there any accessibility issues on this page?"
"Run an accessibility audit."
Identifies loading issues and performance bottlenecks:
"Why is this page loading slowly?"
"Check the performance of this page."
Evaluates search engine optimization factors:
"How can I improve SEO for this page?"
"Run an SEO audit."
Checks adherence to web development standards:
"Run a best practices audit."
"Are there any best practices issues on this page?"
Provides NextJS-specific analysis:
"Run a NextJS audit."
"Run a NextJS audit, I'm using app router."
Runs all audit tools in sequence:
"Run audit mode."
"Enter audit mode."
Executes all debugging tools in sequence:
"Enter debugger mode."
The system consists of three main components:
┌─────────────┐ ┌──────────────┐ ┌───────────────┐ ┌─────────────┐
│ MCP Client │ ──► │ MCP Server │ ──► │ Node Server │ ──► │ Chrome │
│ (e.g. │ ◄── │ (Protocol │ ◄── │ (Middleware) │ ◄── │ Extension │
│ Cursor) │ │ Handler) │ │ │ │ │
└─────────────┘ └──────────────┘ └───────────────┘ └─────────────┘
All logs are stored locally on your machine and are never sent to any third-party service.
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.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
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.
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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.