Skip to main content
Glama

Greeter MCP Server

by jrmlhermitte
  • Linux
  • Apple

MCP Example

Quick and simple repo to demonstrate the very basics MCP and Gemini CLI. Nothing more.

Quick Setup

Quick setup of a new project (using uv):

  1. Install UV
curl -LsSf https://astral.sh/uv/install.sh | sh

(linux and mac)

  1. Clone project and initialize virtualenv
git clone https://github.com/jrmlhermitte/gemini-mcp-example.git cd gemini-mcp-example uv sync source .venv/bin/activate

Write MCP Server And Test

  1. The file we'll run is in gemini-mcp-example/main.py and already defined. Take a look at it. The main components are
# ... mcp = FastMCP("greeter") # ... @mcp.tool() def greet(name: str) -> str: return f'Hello {name}!' # ... if __name__ == "__main__": # NOTE: stdio is the default. mcp.run(transport='stdio')
  1. Run file

(Don't forget to activate your virtual env source .venv/bin/activate)

python gemini-mcp-example/main.py
  1. Init communication

We're going to initialize the 2024-11-05 protocol version using stdin/stdout (the stdio protocol which we setup our fast MCP server to use).

Paste this exactly into your shell:

{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{"roots":{"listChanged":true},"tools":{"listChanged":true},"sampling":{},"elicitation":{}},"clientInfo":{"name":"ExampleClient","title":"ExampleClientDisplayName","version":"1.0.0"}}}

You should see:

{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":"2024-11-05","capabilities":{"experimental":{},"prompts":{"listChanged":false},"resources":{"subscribe":false,"listChanged":false},"tools":{"listChanged":false}},"serverInfo":{"name":"greeter","version":"1.10.1"}}}

NOTE: The json commands here and below must be pasted as is. You cannot have newlines in between. If the formatting is incorrect, the server will just ignore your requests.

When you do, paste this to start the connection:

{"jsonrpc":"2.0","method":"notifications/initialized"}

Now type this to list available tools:

{"jsonrpc":"2.0","method":"tools/list","id":1}

you should see something like this (you may see additional logging):

{"jsonrpc":"2.0","id":1,"result":{"tools":[{"name":"greet","description":"","inputSchema":{"properties":{"name":{"title":"Name","type":"string"}},"required":["name"],"title":"greetArguments","type":"object"},"outputSchema":{"properties":{"result":{"title":"Result","type":"string"}},"required":["result"],"title":"greetOutput","type":"object"}}]}}

Congratulations! You have successfully started a Stdio connection with an MCP server! Now test calling your tool:

{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"greet","arguments":{"name":"Teal'c"}}}

you should then see:

{"jsonrpc":"2.0","id":1,"result":{"content":[{"type":"text","text":"Hello Teal'c!"}],"structuredContent":{"result":"Hello Teal'c!"},"isError":false}}

This is how you're going to setup an MCP server with Gemini.

Gemini CLI will run your server as a child process and send commands to stdin and receive responses from stdout using the stdio protocol.

Gemini CLI

Integrating with Gemini CLI.

  1. Install node
  2. Install Gemini CLI:
npm install -g @google/gemini-cli
  1. Add the Gemini extension from here (docs):

(NOTE: This should be run from the root of this github repo)

mkdir -p ~/gemini/extensions ln -s $PWD/gemini-mcp-example ~/.gemini/extensions
  1. Start gemini and list mcp servers
gemini

Then type:

/mcp

You should see this: mcp

NOTE: You must start gemini from the code folder. The reason is that the extension runs python ./gemini-mcp-example/main.py. If you want to make this runnable from everywhere, you'll need to make sure your base python environment contains the fastmcp library and that the gemini-extension.json refers to an absolute path. NOTE: If this is your first time setting up Gemini CLI, you will also see some easy to follow setup steps.

  1. Give it your name. It will likely try to call your tools.

Input something like:

My name is Teal'c

Gemini should figure that it might want to call the greeting tool, given you've introduced yourself. You should get a request to call the tool: confirmation

And it should hopefully have called the tool. tool_called

Troubleshooting

Running into problems? Try running the mcp server yourself to see if it's able to start up:

source .venv/bin/activate python gemini-extension/main.py

(Also don't forget to run source .venv/bin/activate before starting gemini; We're running this in a local virtual environment here.)

Where to go from here?

This demonstrates how easy it is to setup an MCP server and integrate it with Gemini. You should be able to have a basic enough understanding to integrate it with your own tools now!

-
security - not tested
F
license - not found
-
quality - not tested

A simple demonstration MCP server that provides a greeting functionality when integrated with Gemini CLI.

  1. Quick Setup
    1. Write MCP Server And Test
      1. Gemini CLI
        1. Troubleshooting
          1. Where to go from here?

            Related MCP Servers

            • -
              security
              A
              license
              -
              quality
              The ultimate Gemini API interface for MCP hosts, intelligently selecting models for the task at hand—delivering optimal performance, minimal token cost, and seamless integration.
              Last updated -
              6
              TypeScript
              MIT License
            • -
              security
              A
              license
              -
              quality
              An MCP server that enables other AI models (like Claude) to use Google's Gemini models as tools for specific tasks through a standardized interface.
              Last updated -
              1
              TypeScript
              MIT License
            • -
              security
              -
              license
              -
              quality
              A Model Context Protocol (MCP) server implementation for the Google Gemini language model. This server allows Claude Desktop users to access the powerful reasoning capabilities of Gemini-2.0-flash-thinking-exp-01-21 model.
              Last updated -
              JavaScript
              MIT License
            • A
              security
              A
              license
              A
              quality
              Professional Gemini API integration for Claude and MCP-compatible hosts with intelligent model selection and advanced file handling capabilities.
              Last updated -
              4
              2
              TypeScript
              MIT License

            View all related MCP servers

            MCP directory API

            We provide all the information about MCP servers via our MCP API.

            curl -X GET 'https://glama.ai/api/mcp/v1/servers/jrmlhermitte/gemini-mcp-example'

            If you have feedback or need assistance with the MCP directory API, please join our Discord server