# MCP Remoto — how to use (mcp.ai)

Connect any remote MCP server to your AI. Provide the URL, auth headers and transport, and the remote server's tools become available in your toolkit.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_mcp_proxy?ms=1781044860000`
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. `mcp_proxy_list`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/mcp_proxy`
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/mcp_proxy/_endpoints`

## Example prompts
- "What tools does my connected remote MCP offer?"

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