DEV Community

Google Developer Experts profile image xbill
xbill for Google Developer Experts

Posted on • Originally published at Medium on

MCP Development with C++, Cloud Run, and Gemini CLI

#runcloud #gemini #keith #mcp

Leveraging Gemini CLI and the underlying Gemini LLM to deploy Model Context Protocol (MCP) AI applications built with C++ to Google Cloud Run.

Why not just use Python?

Python has traditionally been the main coding language for ML and AI tools. One of the strengths of the MCP protocol is that the actual implementation details are independent of the development language. The reality is that not every project is coded in Python- and MCP allows you to use the latest AI approaches with other coding languages.

C++? Doesn’t that leak Memory and Crash?

The goal of this article is to provide a minimal viable basic working MCP stdio server in C++ that can be run locally without any unneeded extra code or extensions.

There are a few options for C++ MCP libraries. The C++ MCP library used for the demo is here:

GitHub - hkr04/cpp-mcp: Lightweight C++ MCP (Model Context Protocol) SDK

What Is C++?

C++ is a powerful, high-performance, general-purpose programming language that supports multiple programming paradigms, including object-oriented , procedural , and generic programming. Developed by Bjarne Stroustrup in the early 1980s as an extension of the C language (initially called “C with Classes”), C++ gives developers a high level of control over system resources and memory.

There are several C++ sites but this page is a good starter:

Standard C++

Installing C++

The step by step instructions vary by platform- for a basic Debian system here are the steps:

sudo apt update
sudo apt install build-essential
sudo apt-get install cmake
sudo apt-get install clang-format

g++ --version

xbill@penguin:~$ g++ --version
g++ (Debian 12.2.0-14+deb12u1) 12.2.0
Copyright (C) 2022 Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

xbill@penguin:~$
Enter fullscreen mode Exit fullscreen mode

Gemini CLI

If not pre-installed you can download the Gemini CLI to interact with the source files and provide real-time assistance:

npm install -g @google/gemini-cli
Enter fullscreen mode Exit fullscreen mode

Testing the Gemini CLI Environment

Once you have all the tools and the correct Node.js version in place- you can test the startup of Gemini CLI. You will need to authenticate with a Key or your Google Account:

gemini
Enter fullscreen mode Exit fullscreen mode

Node Version Management

Gemini CLI needs a consistent, up to date version of Node. The nvm command can be used to get a standard Node environment:

GitHub - nvm-sh/nvm: Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions

C++ MCP Documentation

The MCP C++ page provides samples and documentation for getting started:

cpp-mcp/examples/server_example.cpp at main · hkr04/cpp-mcp

Where do I start?

The strategy for starting MCP development is a incremental step by step approach.

First, the basic development environment is setup with the required system variables, and a working Gemini CLI configuration.

Then, a minimal Hello World Style C++ MCP Server is built with HTTP transport. This server is validated with Gemini CLI in the local environment.

This setup validates the connection from Gemini CLI to the local process via MCP. The MCP client (Gemini CLI) and the MCP server both run in the same local environment.

Next- the basic MCP server is deployed to Google Cloud Run. This cloud deployment is validated with a local copy of Gemini CLI running as a MCP client.

Setup the Basic Environment

At this point you should have a working C++ environment and a working Gemini CLI installation. The next step is to clone the GitHub samples repository with support scripts:

cd ~
git clone https://github.com/xbill9/gemini-cli-codeassist
Enter fullscreen mode Exit fullscreen mode

Then run init.sh from the cloned directory.

The script will attempt to determine your shell environment and set the correct variables:

cd gemini-cli-codeassist
source init.sh
Enter fullscreen mode Exit fullscreen mode

If your session times out or you need to re-authenticate- you can run the set_env.sh script to reset your environment variables:

cd gemini-cli-codeassist
source set_env.sh
Enter fullscreen mode Exit fullscreen mode

Variables like PROJECT_ID need to be setup for use in the various build scripts- so the set_env script can be used to reset the environment if you time-out.

Hello World with HTTP Transport

One of the key features that the standard MCP libraries provide is abstracting various transport methods.

The high level MCP tool implementation is the same no matter what low level transport channel/method that the MCP Client uses to connect to a MCP Server.

The simplest transport that the SDK supports is the stdio (stdio/stdout) transport — which connects a locally running process. Both the MCP client and MCP Server must be running in the same environment.

The HTTP transport allows the client and server to run locally or distributed over the Internet.

The connection over HTTP will look similar to this:

    // Create and configure server
    mcp::server::configuration srv_conf;
    srv_conf.host = "0.0.0.0";
    srv_conf.port = port;

    mcp::server server(srv_conf);
    server.set_server_info("mcp-https-cplus", "1.0.0");
Enter fullscreen mode Exit fullscreen mode

C++ Package Information

The code depends on several standard C libraries for MCP and logging:

#include <chrono>
#include <ctime>
#include <filesystem>
#include <functional>
#include <iomanip>
#include <iostream>
#include <map>
#include <mutex>
#include <sstream>
#include <string>
#include <string_view>
#include <vector>

#include "mcp_server.h"
#include "mcp_tool.h"
Enter fullscreen mode Exit fullscreen mode

Installing and Running the C++ Code

Run the install make release target on the local system:

xbill@penguin:~/gemini-cli-codeassist/mcp-https-cplus$ make
Pulling main repository changes...
git pull origin main
From https://github.com/xbill9/gemini-cli-codeassist
 * branch main -> FETCH_HEAD
Already up to date.
Updating all submodules to the latest remote versions...
git submodule update --init --recursive --remote
c++ -std=c++17 -Wall -Wextra -Icpp-mcp/include -Icpp-mcp/common -O2 -c main.cpp
mkdir -p cpp-mcp/build
cd cpp-mcp/build && cmake .. && make mcp
-- The CXX compiler identification is GNU 12.2.0
-- Detecting CXX compiler ABI info
Enter fullscreen mode Exit fullscreen mode

To lint the code:

xbill@penguin:~/gemini-cli-codeassist/mcp-https-cplus$ make lint
clang-format --dry-run --Werror main.cpp
Enter fullscreen mode Exit fullscreen mode

To test the code:

xbill@penguin:~/gemini-cli-codeassist/mcp-https-cplus$ make test
python3 test_server.py
Testing 'greet' tool over HTTP/SSE...
✓ Connected to SSE, message endpoint: /message?session_id=a348a2a7-aa79-0d3c-e363-cf9609d2dc59
✓ initialize successful
✓ notifications/initialized sent
✓ tools/list successful
✓ tools/call (greet) successful

All tests passed!
Enter fullscreen mode Exit fullscreen mode

Gemini CLI settings.json

In this example — the C source code uses a compiled binary that can be called directly from Gemini CLI.

The default Gemini CLI settings.json has an entry for the source:

{
  "mcpServers": {
    "mcp-https-cplus": {
      "url": "http://127.0.0.1:8080/sse"
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Start the Local MCP Server

Open a terminal window and kick off the local MCP server:

xbill@penguin:~/gemini-cli-codeassist/mcp-https-cplus$ make run
./server
{"timestamp":"2026-01-17T17:03:57Z","level":"INFO","message":"Starting MCP HTTP server","data":{"host":"0.0.0.0","port":8080}}
2026-01-17 12:03:57 [INFO] Starting MCP server on 0.0.0.0:8080
2026-01-17 12:03:57 [INFO] Starting server in blocking mode
2026-01-17 12:04:32 [INFO] 127.0.0.1:53864 - "GET /sse HTTP/1.1" -1
2026-01-17 12:04:33 [INFO] 127.0.0.1:53870 - "POST /message HTTP/1.1" 202
2026-01-17 12:04:33 [INFO] Processing method call: initialize
2026-01-17 12:04:33 [INFO] Client requested protocol version: 2025-11-25
2026-01-17 12:04:33 [INFO] Client connected: gemini-cli-mcp-client 0.0.1
2026-01-17 12:04:33 [INFO] Initialization successful, waiting for notifications/initialized notification
2026-01-17 12:04:33 [INFO] 127.0.0.1:53870 - "POST /message HTTP/1.1" 202
2026-01-17 12:04:33 [INFO] 127.0.0.1:53878 - "POST /message HTTP/1.1" 202
2026-01-17 12:04:33 [INFO] Processing method call: tools/list
2026-01-17 12:04:33 [INFO] Calling method handler: tools/list
2026-01-17 12:04:33 [INFO] Method call successful: tools/list
Enter fullscreen mode Exit fullscreen mode

Validation with Gemini CLI

Next- open another window and start Gemini CLI. The local MCP connection over HTTP to the C++ Code is validated and the full Gemini CLI session will start:

> call mcp greet buffer overflow!

✦ I will call the greet tool with the parameter "buffer overflow!".

╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ? greet (mcp-https-cplus MCP Server) {"param":"buffer overflow!"} ← │
│ │
│ MCP Server: mcp-https-cplus │
│ Tool: greet │
│ │
│ Allow execution of MCP tool "greet" from server "mcp-https-cplus"? │
│ │
│ 1. Allow once │
│ 2. Allow tool for this session │
│ ● 3. Allow all server tools for this session │
│ 4. No, suggest changes (esc) │
│ │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ greet (mcp-https-cplus MCP Server) {"param":"buffer overflow!"} │
│ │
│ buffer overflow! │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
Enter fullscreen mode Exit fullscreen mode

Deploying to Cloud Run

After the HTTP version of the MCP server has been tested locally — it can be deployed remotely to Google Cloud Run.

First- switch to the directory with the HTTP MCP sample code:

cd ~/gemini-cli-codeassist/mcp-https-cplus
Enter fullscreen mode Exit fullscreen mode

Deploy the project to Google Cloud Run with the pre-built cloudbuild.yaml and Dockerfile:

cd ~/gemini-cli-codeassist/mcp-https-cplus
xbill@penguin:~/gemini-cli-codeassist/mcp-https-cplus$ make deploy
Enter fullscreen mode Exit fullscreen mode

The Cloud Build will start:

xbill@penguin:~/gemini-cli-codeassist/mcp-https-cplus$ make deploy
Submitting build to Google Cloud Build...
Creating temporary archive of 290 file(s) totalling 5.7 MiB before compression.
Uploading tarball of [.] to [gs://comglitn_cloudbuild/source/1768670570.011261-f8f1037fb7394964800a064b0d5afb03.tgz]
Created [https://cloudbuild.googleapis.com/v1/projects/comglitn/locations/global/builds/62a3353a-0536-40ab-8ba2-c212f968cec0].
Logs are available at [https://console.cloud.google.com/cloud-build/builds/62a3353a-0536-40ab-8ba2-c212f968cec0?project=1056842563084].
Waiting for build to complete. Polling interval: 1 second(s).
----------------------------------------------- REMOTE BUILD OUTPUT ------------------------------------------------
starting build "62a3353a-0536-40ab-8ba2-c212f968cec0"
Enter fullscreen mode Exit fullscreen mode

It can take 15–30 minutes to complete the build.

The cloud build needs to pull in all C++ libraries in the build environment and generate the entire package from scratch.

When the build is complete- an endpoint will be returned:

Starting Step #1
Step #1: Already have image (with digest): gcr.io/cloud-builders/gcloud
Step #1: Deploying container to Cloud Run service [mcp-https-cplus] in project [comglitn] region [us-central1]
Step #1: Deploying...
Step #1: Setting IAM Policy..............done
Step #1: Creating Revision....................................................done
Step #1: Routing traffic.....done
Step #1: Done.
Step #1: Service [mcp-https-cplus] revision [mcp-https-cplus-00007-h4p] has been deployed and is serving 100 percent of traffic.
Step #1: Service URL: https://mcp-https-cplus-1056842563084.us-central1.run.app
Finished Step #1 │
Enter fullscreen mode Exit fullscreen mode

The service endpoint in this example is :

https://mcp-https-cplus-1056842563084.us-central1.run.app
Enter fullscreen mode Exit fullscreen mode

The actual endpoint will vary based on your project settings.

Review Service in Cloud Run

Navigate to the Google Cloud console and search for Cloud Run -

and then you can detailed information on the Cloud Run Service:

Cloud Logging

The remote server writes logs to stderr in standard JSON format. These logs are available from the deployed Cloud Run Service:

Validate HTTP connection

Once you have the Endpoint — you can attempt a connection- navigate to in your browser:

https://mcp-https-cplus-1056842563084.us-central1.run.app
Enter fullscreen mode Exit fullscreen mode

You will need to adjust the exact URL to match the URL returned from Cloud Build.

You will get an error- this connection is expecting a message in the MCP format:

Page Not Found
Enter fullscreen mode Exit fullscreen mode

Gemini CLI settings.json.cloudrun

Replace the default Gemini CLI configuration file —  settings.json with a pre-configured sample- settings.json.cloudrun to use the Cloud Run version of the connection:

 {
    "mcpServers": {
    "hello-cloudrun-cplus": {
               "url": "https://mcp-https-cplus-$PROJECT_NUMBER.us-central1.run.app/sse"
    }
  }
}
Enter fullscreen mode Exit fullscreen mode

Copy the Cloud Run version of the Gemini CLI configuration file:

xbill@penguin:~/gemini-cli-codeassist/mcp-https-cplus$ cd .gemini
cp settings.json.cloudrun settings.json
xbill@penguin:~/gemini-cli-codeassist/mcp-https-cplus/.gemini$
Enter fullscreen mode Exit fullscreen mode

Validation with Gemini CLI

The final connection test uses Gemini CLI as a MCP client with the deployed Cloud Run Service in C providing the MCP server. Startup Gemini CLI with the updated settings :

gemini

/mcp list
 hello-cloudrun-cplus - Ready (1 tool)
  Tools:
  - greet

> greet Cloud Run NULL C++ pointer!

✦ I will call the greet tool with the requested parameter.

╭──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ ✓ greet (hello-cloudrun-cplus MCP Server) {"param":"Cloud Run NULL C++ pointer!"} │
│ │
│ Cloud Run NULL C++ pointer! │
╰──────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
✦ The greet tool returned: "Cloud Run NULL C++ pointer!"
Enter fullscreen mode Exit fullscreen mode

Summary

MCP development with C++ using Gemini CLI was validated with an incremental step by step approach.

A minimal streaming HTTP transport MCP Server was built from source code and validated with Gemini CLI running as a MCP client in the same local environment.

Then — the MCP server was wrapped in a container and submitted to Google Cloud Build for deployment to Google Cloud Run. The remote MCP server was validated with a standard browser, and Gemini CLI.

Finally- remote MCP operations were performed from the local Gemini CLI installation to the C++ MCP server hosted in Google Cloud Run.

This approach can be extended to more complex deployments and Cloud based options.

Top comments (0)