Back to MCP Catalog

Screenpipe MCP Server

Developer ToolsRust
AI-powered desktop history recorder and app store with 24/7 screen and audio capture
Available Tools

screen_recording

Captures and records screen activity continuously

audio_recording

Records microphone input for audio capture and transcription

search_history

Searches through recorded screen and audio history

create_pipe

Creates custom data processing pipelines for captured data

Screenpipe is an open-source tool that continuously records your screen and microphone activity, creating a searchable history of your desktop usage. It runs 100% locally, ensuring your data never leaves your machine while providing a developer-friendly platform for building AI applications on top of your personal data. With Screenpipe, you can create custom "pipes" that process your captured data to automate workflows, enhance productivity, or build personalized AI assistants.

What is Screenpipe?

Screenpipe is an innovative open-source tool that continuously records your screen and microphone activity, creating a comprehensive, searchable history of your desktop usage. It's designed to run entirely locally on your machine, ensuring your data remains private while enabling powerful AI applications to be built on top of your personal data.

Key Features

  • 24/7 Recording: Continuously captures your screen and audio activity
  • 100% Local Processing: All data stays on your machine for maximum privacy
  • Developer-Friendly: Build custom applications using your captured data
  • Pipe Ecosystem: Extensible architecture for creating custom data processing pipelines
  • Cross-Platform: Works on Windows, macOS, and Linux

Installation

To install Screenpipe, follow these steps:

  1. Visit the Screenpipe website and download the appropriate installer for your operating system.
  2. Run the installer and follow the on-screen instructions.
  3. After installation, Screenpipe will start automatically and begin recording your screen and audio (if permitted).

Configuration

When you first run Screenpipe, you'll need to:

  1. Grant screen recording and microphone permissions when prompted
  2. Choose your data storage location (ensure you have sufficient disk space)
  3. Configure recording settings such as resolution, frame rate, and audio quality

You can access these settings at any time through the Screenpipe tray icon or application interface.

Using Screenpipe

Basic Usage

Once installed and configured, Screenpipe runs in the background, continuously recording your screen and audio activity. You can:

  • Access your recording history through the Screenpipe application
  • Search through your history using text or visual queries
  • Create timestamps or bookmarks for important moments

Creating Custom Pipes

Screenpipe's power comes from its extensible "pipe" architecture:

  1. Navigate to the "Pipes" section in the Screenpipe application
  2. Browse available pipes or create your own
  3. Configure pipe settings and activate them
  4. Pipes will process your data according to their functionality

Developer Integration

For developers looking to build on top of Screenpipe:

  1. Clone the repository: git clone https://github.com/mediar-ai/screenpipe
  2. Install dependencies following the instructions in the repository
  3. Explore the API documentation to understand how to interact with Screenpipe data
  4. Create custom pipes using the provided SDK

Privacy and Security

Screenpipe is designed with privacy as a core principle:

  • All data processing happens locally on your machine
  • No data is sent to external servers without your explicit permission
  • You maintain full control over your data, including the ability to delete recordings
  • End-to-end encryption is used for any optional cloud features

Troubleshooting

If you encounter issues with Screenpipe:

  1. Check the application logs (accessible through the settings menu)
  2. Ensure you've granted necessary permissions for screen recording and audio capture
  3. Verify you have sufficient disk space for recordings
  4. Restart the application if it becomes unresponsive
  5. Visit the GitHub repository for known issues or to report new ones

Related MCPs

Apple Shortcuts
Developer ToolsJavaScript

Control Apple Shortcuts automations from AI assistants

Clojars Dependency Lookup
Developer ToolsJavaScript

Fetch dependency information from Clojars, the Clojure community's artifact repository

Simple Timeserver
Developer ToolsPython

Provides Claude with current time and timezone information

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.