# MCP

> MCP is an MCP server for productivity. Lets agents record a web app, then search and read your Clipy recordings. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Free trial
- **Starting price:** $9 a month
- **Platforms:** API, CLI, Web
- **Website:** https://clipy.online/mcp
- **Repository:** https://github.com/clipy-recorder/clipy-mcp
- **MCP Registry name:** online.clipy/mcp
- **Categories:** productivity, developer tools
- **Listing updated:** 2026-11-14

## About

Recording runs in headless Chromium: the agent starts a capture, drops timestamped markers as it works through each step, and stops to receive a share link plus a URL with agent context. Afterwards the same server can search recordings by keyword, pull the timestamped transcript, and fetch the AI summary with key points and action items.

There are two ways in. The local server (npx @clipy/mcp) uses a Clipy API key and needs the record-and-upload scope to capture; a hosted endpoint at clipy.online/api/mcp signs in with OAuth and is aimed at searching and reading a library from ChatGPT or Claude without installing anything.

The tool list also covers chapters, transcript editing and downloading the MP4 so an agent can clip it. It suits teams that already keep screen recordings in Clipy and want coding agents to demonstrate or review changes with them.

## Features

- **Agent-driven recording:** Starts a headless Chromium capture, adds markers and returns a share link on stop.
- **Library search:** Finds recordings by keyword across titles and descriptions.
- **Transcripts and summaries:** Reads timestamped transcripts and AI summaries with key points and action items.
- **Hosted OAuth endpoint:** Connects ChatGPT or Claude to a library without a local process or API key.
- **Recording edits:** Adds chapters, edits transcripts and downloads the MP4.

## Good for

- Have a coding agent record a walkthrough of a bug it just fixed
- Ask an assistant what was decided in last week's recorded review
- Pull action items from a recording into a ticket
- Find the moment in a demo where a feature is shown

## Install

### Claude Code (Terminal)

```sh
claude mcp add mcp --env CLIPY_API_KEY='<CLIPY_API_KEY>' -- npx -y @clipy/mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@clipy/mcp"
      ],
      "env": {
        "CLIPY_API_KEY": "<CLIPY_API_KEY>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@clipy/mcp"
      ],
      "env": {
        "CLIPY_API_KEY": "<CLIPY_API_KEY>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@clipy/mcp"
      ],
      "env": {
        "CLIPY_API_KEY": "<CLIPY_API_KEY>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@clipy/mcp"
      ],
      "env": {
        "CLIPY_API_KEY": "<CLIPY_API_KEY>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@clipy/mcp"
      ],
      "env": {
        "CLIPY_API_KEY": "<CLIPY_API_KEY>"
      }
    }
  }
}
```

## Tools

- `start_recording`: Begin a headless Chromium recording of a web app
- `add_marker`: Add a timestamped marker during a recording
- `stop_recording`: Upload the capture and return the share link and agent-context URL
- `search_recordings`: Find a recording by keyword across titles and descriptions
- `get_transcript`: Read the full timestamped transcript
- `get_summary`: Pull the AI summary: TL;DR, key points, action items
- `list_recordings`: Browse recent recordings, newest first
- `wait_for_artifacts`: Poll until transcript and summary finish processing
- `get_recording`: Get one recording's metadata and status
- `download_recording`: Download the MP4 locally

## FAQ

### Do I need a local install?

No. The hosted endpoint https://clipy.online/api/mcp signs in with OAuth. Recording a web app runs from the local npx @clipy/mcp server with an API key.

### Which key scope does recording need?

The key needs the Record & upload scope. Searching and reading works with a read key or OAuth.

### Is it free?

Clipy offers a seven-day free trial with no card; Pro is shown at $9 a month paid monthly, with a discounted first annual year at the time of the page.

### Is MCP free?

MCP is a paid product with a free trial. Paid plans start at $9 a month.

### How do I add MCP to Claude Code?

Run this command in your terminal: claude mcp add mcp --env CLIPY_API_KEY='<CLIPY_API_KEY>' -- npx -y @clipy/mcp

### What are the best alternatives to MCP?

The closest alternatives to MCP are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ha MCP](https://ai-powered.com/mcp/ha-mcp): Ha MCP is an open-source MCP server for productivity.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/mcp-mwepf6cd
