Prepare your Python project

The following steps describe how toset up your Python project with theuv package manager.

1. Create a folder namedmcp-on-cloudrun to store the source code fordeployment:

     mkdir mcp-on-cloudrun  cd mcp-on-cloudrun

2. Create a Python project with theuv tool to generate apyproject.toml file:

     uv init --name "mcp-on-cloudrun" --description "Example of deploying an MCP server on Cloud Run" --bare --python 3.10

   Theuv init command creates the followingpyproject.toml file:

   [project]name="mcp-server"version="0.1.0"description="Example of deploying an MCP server on Cloud Run"readme="README.md"requires-python=">=3.10"dependencies=[]

3. Create the following additional new files:

   • server.py for the MCP server source code
   • test_server.py to test the remote server
   • A Dockerfile for deploying to Cloud Run

   touch server.py test_server.py Dockerfile

   Your project directory should contain the following structure:

   ├── mcp-on-cloudrun│   ├── pyproject.toml│   ├── server.py│   ├── test_server.py│   └── Dockerfile

Create an MCP server for math operations

To provide valuable context for improving the use of LLMs with MCP, set up amath MCP server withFastMCP.FastMCP provides a quick way to build MCP servers and clients with Python.

Follow these steps to create an MCP server for math operations such asaddition and subtraction.

1. Run the following command to add FastMCP as a dependency in thepyproject.toml file:

   uv add fastmcp==2.13.1 --no-sync

2. Add the following math MCP server source code in theserver.py file:

   importasyncioimportloggingimportosfromfastmcpimportFastMCPlogger=logging.getLogger(__name__)logging.basicConfig(format="[%(levelname)s]:%(message)s",level=logging.INFO)mcp=FastMCP("MCP Server on Cloud Run")@mcp.tool()defadd(a:int,b:int)->int:"""Use this to add two numbers together.    Args:        a: The first number.        b: The second number.    Returns:        The sum of the two numbers.    """logger.info(f">>> 🛠️ Tool: 'add' called with numbers '{a}' and '{b}'")returna+b@mcp.tool()defsubtract(a:int,b:int)->int:"""Use this to subtract two numbers.    Args:        a: The first number.        b: The second number.    Returns:        The difference of the two numbers.    """logger.info(f">>> 🛠️ Tool: 'subtract' called with numbers '{a}' and '{b}'")returna-bif__name__=="__main__":logger.info(f"🚀 MCP server started on port{os.getenv('PORT',8080)}")# Could also use 'sse' transport, host="0.0.0.0" required for Cloud Run.asyncio.run(mcp.run_async(transport="streamable-http",host="0.0.0.0",port=os.getenv("PORT",8080),))

3. Include the following code in the Dockerfile to use theuv tool for running theserver.pyfile:

   # Use the official Python imageFROMpython:3.13-slim# Install uvCOPY--from=ghcr.io/astral-sh/uv:latest/uv/uvx/bin/# Install the project into /appCOPY./appWORKDIR/app# Allow statements and log messages to immediately appear in the logsENVPYTHONUNBUFFERED=1# Install dependenciesRUNuvsyncEXPOSE$PORT# Run the FastMCP serverCMD["uv","run","server.py"]

Deploy to Cloud Run

You can deploy the MCP server as acontainer image or assource code:

gcloud run deploy mcp-server --no-allow-unauthenticated --region=us-central1 --source .

Authenticate MCP client

If you deployed your service with the--no-allow-unauthenticated flag, any MCP clientthat connects to your remote MCP server must authenticate.

1. Grant theCloud Run Invoker (roles/run.invoker) role to the service account. ThisIdentity and Access Management policy binding makes sure that a strong security mechanism is used to authenticate your local MCP client.

2. Run theCloud Run proxyto create an authenticated tunnel to the remote MCP server on your localmachine:

   gcloud run services proxy mcp-server --region=us-central1

   If the Cloud Run proxy is not yet installed, this command promptsyou to download the proxy. Follow the prompts to download and install the proxy.

Cloud Run authenticates all traffic tohttp://127.0.0.1:8080 and forwardsrequests to the remote MCP server.

Test the remote MCP server

You test and connect to the remote MCP server by using the FastMCP client and accessingthe URLhttp://127.0.0.1:8080/mcp.

To test and invoke the add and subtract mechanism, follow these steps:

1. Before running the test server,run the Cloud Run proxy.

2. Create a test file calledtest_server.py and add the following code:

   importasynciofromfastmcpimportClientasyncdeftest_server():# Test the MCP server using streamable-http transport.# Use "/sse" endpoint if using sse transport.asyncwithClient("http://localhost:8080/mcp")asclient:# List available toolstools=awaitclient.list_tools()fortoolintools:print(f">>> 🛠️  Tool found:{tool.name}")# Call add toolprint(">>> 🪛  Calling add tool for 1 + 2")result=awaitclient.call_tool("add",{"a":1,"b":2})print(f"<<< ✅ Result:{result[0].text}")# Call subtract toolprint(">>> 🪛  Calling subtract tool for 10 - 3")result=awaitclient.call_tool("subtract",{"a":10,"b":3})print(f"<<< ✅ Result:{result[0].text}")if__name__=="__main__":asyncio.run(test_server())

3. In a new terminal, run the test server:

   uv run test_server.py

   You should see the following output:

    🛠️ Tool found: add 🛠️ Tool found: subtract 🪛 Calling add tool for 1 + 2 ✅ Result: 3 🪛 Calling subtract tool for 10 - 3 ✅ Result: 7