Screenpipe MCP server

Enable searching and retrieving screen recordings and associated data for productivity tracking, user behavior analysis, and workflow documentation.
Back to servers
Provider
Mediar AI
Release date
Dec 31, 2024
Language
Python
Stats
14.7K stars

Screenpipe-MCP is a Model Context Protocol server that connects Claude AI to your screen recordings. This server allows Claude to search through your screen content including text (OCR), audio transcriptions, and UI elements, making it possible to ask questions about what appeared on your screen in the past.

Installation

Prerequisites

  • Claude Desktop app
  • Git
  • Python with uv package manager

Setup Instructions

  1. Download the Claude desktop app from claude.ai/download

  2. Clone the repository:

    git clone https://github.com/mediar-ai/screenpipe
    
  3. Edit the Claude app configuration file:

    Windows:

    notepad $env:AppData\Claude\claude_desktop_config.json
    

    Mac:

    code "~/Library/Application Support/Claude/claude_desktop_config.json"
    
  4. Add the following configuration to the JSON file:

    {
        "mcpServers": {
            "screenpipe": {
                "command": "uv",
                "args": [
                    "--directory",
                    "/absolute/path/to/screenpipe-mcp",
                    "run",
                    "screenpipe-mcp"
                ]
            }
        }
    }
    
  5. Restart Claude Desktop after saving the configuration changes

Testing the Server

Using MCP Inspector

To verify the server is working correctly, test it with the MCP Inspector:

npx @modelcontextprotocol/inspector uv run screenpipe-mcp

Testing with Claude

Once installed, you can interact with your screen recordings by asking Claude questions like:

  • "Search for any mentions of 'rust' in my screen recordings"
  • "Find audio transcriptions from the last hour"
  • "Show me what was on my screen in VSCode yesterday"

Features and Usage

Search Parameters

The MCP server supports various search parameters:

  • Full text search - Find specific text that appeared on your screen
  • Content type filtering - Filter by OCR (text on screen), audio transcriptions, or UI elements
  • Time range filtering - Limit results to specific time periods
  • App/window filtering - Search within specific applications
  • Length constraints - Control how many results are returned
  • Pagination - Navigate through large result sets

Response Formats

Results are formatted for optimal readability in Claude's interface:

  • Clear organization by content type
  • Relevant metadata with each result
  • Timestamps and source information
  • Formatted for easy consumption

Troubleshooting

  • Ensure the Screenpipe server is running on port 3030
  • The server assumes a local connection by default
  • All timestamps are processed in UTC
  • If you receive no results, check your query parameters or confirm that screen recording was active during the requested time period

How to add this MCP server to 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 > 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"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later