TL;DR
Screenpipe is a AI & agents MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent search locally captured screen text and audio history to recover prior work, meeting details, and context for AI assistants. Install in 1 minute with mcpizy install screenpipe.
Screenpipe
AI & agents
Search locally captured screen text and audio history to recover prior work, meeting details, and context for AI assistants. Runs on macOS, Windows, and Linux; requires a running Screenpipe instance with captured data. Recommended setup: desktop app Settings > Connections. Manual setup: npx -y screenpipe-mcp@latest, Node.js 18+, and local API authentication as documented in the README. Source-available under the Screenpipe Commercial License, not MIT or OSI open source: https://github.com/screenpipe/screenpipe/blob/main/LICENSE.md . Local storage is the default; retrieved context goes to the connected assistant's model, and optional cloud features can send data off-device. The stdio server includes action tools as well as search. Current plans: https://screenpipe.com/pricing . Submitted by Louis, Screenpipe maintainer.
Install Screenpipe
mcpizy install screenpipeWe could not verify a published package or a reachable endpoint for this server, so we are not showing an install command that would fail. Checked 2026-08-11. Follow the repository's own instructions instead.
Works with
More AI & agents MCPs
iLook Face Analysis
iLook analyses authorised adult face photos with non-medical face-shape, visible symmetry and presentation feedback, plus a separate approximate phi score. Its remote Streamable HTTP MCP server lets AI agents run consent-based analysis workflows.
VoxelDraft
VoxelDraft is a hosted MCP server for creating, editing, inspecting, rendering, animating, and exporting voxel models. It provides browser-native voxel tooling to AI agents through a public remote endpoint.
councilof ai
Public 22-axis AI governance measurement with signed evidence cards, independently verifiable roots, MCP and A2A access, and x402-compatible proof delivery.
NoClick
Build agents to automate any background task. Works with your ChatGPT/Claude subscription.
Alternatives to Screenpipe
If Screenpipe doesn't fit your stack, these AI & agents MCP servers solve similar problems.
Humanizer PRO MCP
Hosted OAuth MCP for rewriting authorized draft text with natural readability, scanning AI-style signals, and checking word-balance patterns.
Sauna Guide Quotes
Prepare a home sauna project brief, review missing details, and submit a quote request only after explicit buyer approval.
iLook Face Analysis
Remote MCP server for iLook’s privacy-first facial-analysis API. It lets agents request non-medical visible-signal feedback for authorised adult photos; it does not perform identity recognition, age verification, or sensitive-trait inference.
Frequently asked questions
What is the Screenpipe MCP server?
Screenpipe is listed as an AI & agents Model Context Protocol server whose documented purpose is to let an MCP-compatible agent search locally captured screen text and audio history to recover prior work, meeting details, and context for AI assistants. Client support, permissions and authentication remain specific to the upstream project.
How do I install Screenpipe MCP with Claude Code?
The fastest way is the MCPizy CLI: run `mcpizy install screenpipe` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `null` and restarting Claude Code.
Does MCPizy charge to view or install Screenpipe MCP?
No. Reading this profile and copying its install guidance is free. Upstream software, API, account or usage costs are separate, and licence coverage should be checked from the linked source when available.
Does Screenpipe MCP work with Cursor and Windsurf?
The MCP standard is supported by those clients, but a specific server can still have client-specific setup or transport limits. Use the configuration shown on this page when present and verify the upstream instructions before installation.
What can I do with Screenpipe MCP?
Its documented purpose is to let an MCP-compatible agent search locally captured screen text and audio history to recover prior work, meeting details, and context for AI assistants. The exact tools, permissions and write capabilities depend on the server version and configuration shown by the upstream project.
Compare before you commit
Put this server beside an alternative, or return to the full evidence directory.
Compare MCP serversBack to directory