Skip to content

MCP Integration

The Model Context Protocol (MCP) is an open standard that enables AI applications to connect to any external tool or data source without custom integration for every service.

What is MCP?

Think of MCP as a "USB port for AI." Just as a USB port allows you to connect any device to your computer, MCP allows Backend.AI GO to connect to any "MCP Server" that provides tools and data.

Why use MCP?

  • Extensibility: Connect the AI to your proprietary databases, local Slack, specialized APIs, or your own custom scripts.
  • Community Ecosystem: Use a wide range of open-source MCP servers developed by the community.
  • Standardization: One protocol to rule them all—once you set up an MCP server, it works across any MCP-compatible AI client.

Connecting MCP Servers

Backend.AI GO can connect to MCP servers via stdio transport (running a local process).

  1. Navigate to Settings > MCP Integration.
  2. Click Add Server.
  3. Enter a name for the server.
  4. Specify the command (e.g., node, python, npx).
  5. Add any required arguments or environment variables (like API keys).
  6. Click Connect.

Managing MCP Tools

Once connected, the tools provided by the MCP server will automatically appear in your Agent Settings.

  • You can toggle individual MCP servers on or off.
  • The Agent will treat MCP tools just like built-in tools, including full permission and approval support.
  • You can see the list of discovered tools by clicking "Details" on a connected MCP server.

For a list of popular MCP servers, visit the MCP Server Directory.