Skip to content
zero2vibecodelearn vibe coding
Google CloudBy Mikhail Kuzmitskii

What Google Cloud API Gateway's MCP Support Means for Beginners

Based on the vendor announcement linked above — written with AI assistance and reviewed by the author.

In short

Google Cloud API Gateway now lets you expose existing REST APIs as MCP tools without running separate servers. Here's what changes for beginners building AI agents.

When you build AI agents that need to interact with real services, those services typically live behind REST APIs. Until now, making one usable by an agent required setting up an entirely separate Model Context Protocol (MCP) server — duplicating the authentication, routing, and quotas your API gateway already handles.

A bridge connecting two servers with API symbols floating between them

Google Cloud API Gateway now removes that friction. In Public Preview, you can annotate your existing OpenAPI spec to expose REST operations as MCP tools directly through the gateway — no extra infrastructure needed.

Why this matters for beginners

If you’re learning to build agents with frameworks like the Agent Development Kit (ADK) or Gemini Enterprise, MCP is the standard way your agent discovers and calls tools. Previously:

  • Tool setup was complex: You needed to run and maintain an MCP server that mirrored your API gateway’s logic
  • Policies diverged: Authentication and quotas for REST vs. MCP calls could drift apart
  • Discovery was manual: Agents couldn’t automatically find available tools

Now:

BeforeAfter
Separate MCP server requiredMCP served directly from API Gateway
Policies maintained in two placesOne set of auth/quota rules covers both REST and MCP
Tools registered manuallyGateway publishes to API Hub and Agent Registry automatically

Tip

This doesn’t replace Apigee for full enterprise API management or Agent Gateway for outgoing call governance. It’s the lightweight path for services on Cloud Run.

How it works technically

  1. Annotate your OpenAPI spec:
    • Enable MCP at the document level with x-google-api-management.mcp
    • Customize tool behavior per operation with x-google-mcp-tool
    • Critical: Write descriptive tool explanations — LLMs use these to decide when to call them
x-google-mcp-tool:  
  name: get_order_status  
  description: "Look up delivery status and ETA. Use when asked where an order is or when it will arrive."  
  1. Deploy normally: The gateway generates MCP support automatically on the /mcp path

  2. Control discovery: Secure tools/list with JWT (API keys won’t work here) while tools/call inherits your REST operation’s auth

  3. Connect your agent: Point any MCP client like ADK to the gateway’s /mcp endpoint with your existing credentials

What you can do now

  • Expose existing APIs: Turn well-documented REST operations into agent tools in minutes
  • Maintain one policy set: Authentication and quotas apply consistently whether called via REST or MCP
  • Publish discoverably: Gateways with MCP enabled automatically appear in API Hub and Agent Registry

Current limitations

While in Public Preview:

  • No support for OpenAPI 2.0 — migrate to 3.x first
  • Operations returning HTTP 204 (no content) can’t be exposed
  • Maximum 1,000 tools per gateway
  • No MCP + model routing in the same API config

Getting started

  1. Migrate to OpenAPI 3.x if needed
  2. Annotate your spec with MCP metadata
  3. Deploy to API Gateway as usual
  4. Connect your agent to the /mcp endpoint

Important

Tool descriptions directly impact whether your agent calls them correctly. Focus on when and why to use the tool, not just what it returns.

For beginners, this eliminates a major infrastructure hurdle when connecting agents to real services. Instead of operating parallel systems, you can focus on designing useful tool interactions.

Want to try all of this hands-on? Start with the free Claude Code from Zero course.

Source

Based on Google’s announcement, “Turn your REST APIs into MCP tools with Google Cloud API Gateway”. Written for people learning to build with these tools.

Read next

Try it hands-on

Free interactive courses on this topic — in your browser, from zero.