# Devin MCP — how to use (mcp.ai)

Connect your Devin MCP account and use 4 tools for model context protocol straight from your AI agent. Connect with your own API key. AI-powered access to GitHub repository documentation and codebase analysis, including private repositories, via Devin.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_devin_mcp?ms=1787295960000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `devin_mcp_ask_question`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/devin_mcp`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/devin_mcp/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/devin_mcp/ask/question` — Ask any question about a GitHub repository and get an AI-powered, context-grounded response.
  - body: { question: string, repoName: string|string[] }
- `POST https://api.mcp.ai/api/devin_mcp/list/available/repos` — List all repositories available to query with your Devin account.
- `POST https://api.mcp.ai/api/devin_mcp/read/wiki/contents` — View documentation about a GitHub repository.
  - body: { repoName: string }
- `POST https://api.mcp.ai/api/devin_mcp/read/wiki/structure` — Get a list of documentation topics for a GitHub repository.
  - body: { repoName: string }

## Example prompts
- "What can I do in Devin MCP?"
- "Show me a summary of my Devin MCP account"

## More
- Page: https://mcp.ai/devin_mcp
- Agent spec (llms.txt): https://mcp.ai/devin_mcp/llms.txt
- Postman collection: https://mcp.ai/devin_mcp/postman.json