Screenpipe logo

Screenpipe

Search locally captured screen, audio, meetings, apps, and memories through MCP, then create notes, reports, and scheduled automations.

Install Screenpipe

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "screenpipe": {
      "command": "npx",
      "args": [
        "-y",
        "screenpipe-mcp@latest"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 34 tools correctly ().

Overview

screenpipe MCP server connects MCP clients to screenpipe’s local capture and memory system, covering screen activity, audio, app context, meetings, speakers, and accessibility data. Its tools support precise content and keyword searches, broad activity recaps, meeting retrieval, persistent memories, notifications, recording controls, and scheduled pipes. Reach for it when an agent needs evidence from recent computer work, cross-device history, meeting context, or recurring reports. Capture and local search work offline after setup, while sync, cloud AI, and connected services require network access.

Use cases

  • Summarize a work session from captured activity
  • Find a quoted line in screen or audio history
  • Reconstruct a meeting with its transcript and notes
  • Save durable project facts as tagged memories
  • Schedule recurring reports with pipes

Key features

  • Local screen, audio, meeting, and app-history search
  • Activity summaries with active-minute evidence
  • Meeting, speaker, and transcript management
  • Persistent memories and shared capture tags
  • Timestamp-accurate video export
  • Scheduled AI automations with execution logs

Tools34

What Screenpipe lets your agent do. Expand a tool for its parameters.

Verified live~7.4k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked

Recent health check succeeded.

61/61 checks healthy over the last 89d

What it can do

From the 34 tools this server returned when we ran it; 34 declare their own safety hints.

Runs commands · 1Can delete or modify data · 2Makes network requests · 2Read-only tools · 31
Network at startup4 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age292 days
Maintainers1

Observed 2026-11-10 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 14d ago via OSV.dev · screenpipe-mcp@latest (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars22kStargazers on the source repository.
Last commitTodayMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed34Callable tools this server registers over MCP.
Directory activity18 viewsConfig copies, upvotes, and views on AllMCPs.

How Screenpipe works

What screenpipe MCP server does

screenpipe MCP server gives an MCP client access to screenpipe’s searchable record of computer activity. The underlying application captures screen content, accessibility trees, OCR, audio, transcriptions, speakers, keyboard input, and app switches, with history stored locally by default. Agents can use that history to answer questions about what happened, locate exact text, reconstruct meetings, create cited notes, and identify repeatable workflows.

The server also exposes durable memory and automation features. An agent can save facts, preferences, or decisions; attach shared tags to captures and memories; send notifications to the desktop UI; and create scheduled pipes that run a markdown prompt against screenpipe data.

How it works

Install and run the screenpipe desktop app or CLI so capture data is available, then connect an MCP client to the package using standard input/output. Search tools query local records, while meeting and speaker tools provide more structured access to conversations. Data Sync tools search records uploaded by the signed-in user’s other devices and return device attribution.

Use the tool that matches the question:

  • activity-summary is for broad time-based recaps, app usage, active minutes, edited paths, and transcription context.
  • search-content finds specific content with filters such as speaker, window, content type, and time range.
  • keyword-search provides fast OCR and audio phrase matching.
  • search-elements, get-frame-elements, and frame-context inspect controls, accessibility nodes, URLs, and frame details.
  • list-meetings followed by get-meeting retrieves meeting metadata, notes, and optional speaker-attributed transcripts.

Setup and configuration

Download the desktop application for macOS, Windows, or Linux, or start capture with:

Terminal
npx screenpipe record

The CLI can configure the MCP connection:

Terminal
npx screenpipe setup

For Claude, the server can be added directly with:

Terminal
claude mcp add screenpipe -- npx -y screenpipe-mcp@latest

The setup flow also installs screenpipe skills and MCP configuration into supported coding agents detected on the computer. The CLI documentation emphasizes verifying capture freshness and storage before querying history.

Tools and capabilities

  • Search screen text, audio transcripts, input events, memories, parsed application data, and synced-device records.
  • Summarize activity by app, window, active minutes, edited documents, and time range.
  • List, inspect, update, and manually control meeting recordings.
  • Search, rename, update, and merge recognized speakers.
  • Export timestamp-accurate MP4 clips with synchronized microphone audio.
  • Create, update, delete, retrieve, and tag persistent memories and captured frames or audio.
  • List, create, run, and inspect scheduled AI pipes.
  • Check service health and enumerate monitors or audio devices.

Limitations and notes

Capture consumes approximately 5–20% CPU and 0.5–3 GB of RAM before additional local models or workloads. Storage requirements depend on activity, displays, audio, capture settings, and retention, so measure usage on the target machine. Screen and audio history can be filtered by window, application, Chrome extension, passwords, and proprietary AI personal-information rules; encryption at rest is optional.

Frames are subject to retention and may be pruned, so durable relationships should be represented with tagged memories. Search results may be truncated unless a different content length is requested. Local capture and search function offline after setup, but cloud AI, synchronization, and connected services need network access. The application is source-available, and local history remains on the device by default unless optional cloud or team paths are used.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Screenpipe

screenpipe is an MCP server that connects AI clients to screenpipe’s local record of screen, audio, app, and meeting activity. Its main tools search captured content, summarize activity, retrieve meetings and transcripts, manage memories, export recordings, inspect UI elements, and run scheduled pipes for recurring workflows.

Install screenpipe’s desktop app or start capture with `npx screenpipe record`, then run `npx screenpipe setup`. For Claude, use `claude mcp add screenpipe -- npx -y screenpipe-mcp@latest`. The setup command can also configure supported coding agents detected on the computer.

Yes, screenpipe supports Cursor as a coding agent. Run `npx screenpipe setup` to install the screenpipe skills and MCP configuration into supported agents detected on the computer, or configure the MCP server using the client’s standard stdio setup.

Yes, use `synced-devices` to identify devices with uploaded Data Sync records, then use `search-synced-content` with the exact device name when needed. For the machine currently running screenpipe, use `search-content` instead.

Yes, its pipe tools create scheduled AI automations from markdown prompts. Use `list-pipes` to inspect existing automations, `create-pipe` to install and test one, `run-pipe` for an immediate run, and `pipe-logs` to review execution results.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewScreenpipe AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/screenpipe?style=directory)](https://allmcps.com/mcp/screenpipe)
HTML Embed
<a href="https://allmcps.com/mcp/screenpipe"><img src="https://allmcps.com/api/badge/screenpipe?style=directory" alt="Screenpipe on AllMCPs" /></a>