MCP Bridge: Expose APIs as AI Agent Tools

⏱ 20 min

What is MCP Bridge?

The Model Context Protocol (MCP) is an open standard that lets AI agents discover and call external tools. MuleSoft’s MCP Bridge is an Omni Gateway capability that converts your existing REST APIs into MCP-compatible tools — without modifying the APIs themselves.

AI Agent (Claude, GPT, etc.)
        │
        │  MCP Protocol
        ▼
   MCP Bridge (Omni Gateway)
        │
        │  HTTP/REST
        ▼
  Your Existing APIs  ──▶  Backend Systems

Instead of building a custom MCP server from scratch, MCP Bridge reads your APIs already published in Anypoint Exchange and exposes them as typed, discoverable tools that any MCP-compatible agent can invoke.

Why it matters

Traditional API integration requires developers to write client code for every API call. With MCP Bridge:

An AI agent can discover what tools are available at runtime
Each tool has a name and description the agent uses to decide when to call it
The agent passes natural-language intent; the bridge maps parameters to the right HTTP call
No new Mule application code is needed — the Omni Gateway handles everything

What you’ll build

By the end of this workshop you will have:

Published a sample REST API to Anypoint Exchange
Deployed an MCP Bridge instance on an Omni Gateway
Mapped API endpoints to MCP tools with names and descriptions
Tested tool invocation end-to-end from an AI agent perspective

Estimated time

Section	Duration
Concepts & prerequisites	5 min
Publish API to Exchange	5 min
Create MCP Bridge instance	5 min
Test & verify	55 min

Ready? Start with Prerequisites →