recit
Free, open-source screen recording MCP server for AI agents. Enables screen capture, screenshots, and frame extraction locally without cloud dependencies.
README
recit
Record it. Agents see it.
Free, open-source screen recording CLI + MCP server for AI agents. Zero cost. 100% local. No cloud. No API keys.
Features
- Screen Recording — Capture full screen, windows, or regions via ffmpeg
- Screenshots — Instant PNG capture with JSON metadata output
- MCP Server — 5 tools exposed via Model Context Protocol (stdio)
- Frame Extraction — Scene-detection key frames for vision model analysis
- Event Logging — JSONL event log synced to video clock (clicks, keystrokes, annotations)
- Cross-Platform — macOS, Windows, Linux
- $0 Cost — No APIs, no cloud, no hosting, no subscriptions
Quick Start
# For Claude Code
claude mcp add recit -- npx -y @recit/mcp
# For Cursor / VS Code — add to mcp.json:
{
"mcpServers": {
"recit": {
"command": "npx",
"args": ["-y", "@recit/mcp"]
}
}
}
# Prerequisites (both free)
brew install ffmpeg # macOS
sudo apt install ffmpeg # Ubuntu/Debian
winget install ffmpeg # Windows
CLI Usage
# Start recording
recit start [--output path] [--fps 15] [--json]
# Stop recording
recit stop <id> [--json]
# Capture screenshot
recit snap [--output path] [--json]
# Extract frames from video
recit frames <video> [--max 20] [--output dir]
# Check recording status
recit status [id]
# Start MCP server
recit mcp
MCP Tools
| Tool | Description |
|---|---|
recit_start |
Start screen recording |
recit_stop |
Stop recording, get file path |
recit_snap |
Capture screenshot |
recit_frames |
Extract key frames from video |
recit_status |
Get recording status or active count |
Architecture
AI Agent (Claude/Codex/Cursor)
│
│ stdio (stdin/stdout)
▼
recit MCP Server (Node.js, local)
│
│ child_process
▼
ffmpeg (free, local)
│
▼
.mp4 / .png saved to user's disk
$0 spent. Nothing uploaded. Everything local.
Development
git clone https://github.com/recit-ai/recit.git
cd recit
npm install
npm test # Run 43 tests
npm run build # Build TypeScript
Tech Stack
| Layer | Tool | Cost |
|---|---|---|
| Recording | ffmpeg | $0 |
| Agent Integration | MCP SDK (stdio) | $0 |
| Distribution | npm | $0 |
| Code Hosting | GitHub | $0 |
| Runtime | Node.js | $0 |
| Testing | Vitest | $0 |
License
Apache 2.0
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.