Overview
Add the Reap documentation MCP server to your AI coding agent so it can search and read the full Reap API reference on the fly. Your agent gets live access to endpoints, schemas, authentication details, and workflows — no skill files to maintain. Supported agents include Cursor, VS Code, GitHub Copilot, Claude Code, Codex, Gemini CLI, and 30+ more.Install with CLI
Run the following command in your project directory:Select Agents
Choose which agents to install to. Cursor, VS Code, and GitHub Copilot are pre-selected. You can also pick from 30+ additional agents.
Review Summary
Review the installation summary — server name, type (remote), scope (project), and selected agents.
Done! Your agent can now search and read the Reap API docs directly during conversations.
Manual Setup
If you prefer to configure manually, add the following to your agent’s MCP config file.- Cursor / VS Code
- Claude Code
Add to
.cursor/mcp.json or .vscode/mcp.json in your project root:What Can Your Agent Do With MCP?
Once connected, your agent has live access to the full Reap API documentation. You can ask it to:Build Integrations
“Integrate Reap clipping into my Express backend”
Create Pipelines
“Build a pipeline that uploads a video, creates clips, and polls for completion”
Generate Code
“Write a Python script that creates a caption project with the Reap API”
Debug API Calls
“Why is my create-reframe call returning 400?”
MCP vs Agent Skills
Both approaches give your agent knowledge of the Reap API. Choose based on your preference:| MCP | Agent Skills | |
|---|---|---|
| How it works | Agent queries a live remote server | Skill files stored in your project |
| Always up to date | Yes — reads live docs | Manual re-run to update |
| Offline support | No | Yes |
| Install method | npx add-mcp or manual JSON | npx skills add |
Learn More
- addmcp.com — Browse and manage MCP servers
- Agent Skills — Offline alternative using skill files
- Quickstart — Get started with the Reap API
- Authentication — Set up your API key