MCP Project Setup

This document outlines the steps to set up themcpproject environment.

Create a new conda environment namedmcpwith Python 3.12:

Install theuvpackage manager using the following command:

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

Install thefastmcppackage usinguvin themcpenvironment:

Confirm thefastmcpinstallation by running the following command:

mcp_hello.pyis a "hello world" type mcp server. You can run the MCP inspector for it using the following command:

conda run -n mcp fastmcp dev mcp_hello.py:mcp

Copy the provided session token from CLI, click on the provided link, paste in Configuration -> Proxy Session Token, click connect.

Click on Tools in the top menu bar. "hello_world" should be listed with a parameter "name". Input your name and click "Run Tool". The tool should succeed and return a greeting.

mcp_resources.pydefines MCP resources. You can run tests for these resources using the--testargument:

mcp_weather.pyexposes a tool to get current weather data from OpenWeatherMap.

Before running:Ensure you have set yourOPENWEATHER_API_KEYin the.envfile:

conda run -n mcp fastmcp dev mcp_weather.py:mcp

To allow the Gemini CLI to automatically start and connect to yourmcp_weatherserver, you need to configure itssettings.jsonfile.
-

Locatesettings.json:Thesettings.jsonfile is typically located at:

- Linux/macOS:~/.gemini/settings.json
- Windows:%APPDATA%\gemini\settings.json

If the file or directory does not exist, create them.

AddmcpServersentry:Add the following entry to themcpServerssection in yoursettings.jsonfile. Replace/mnt/d/Projects/_sandbox/mcp/with the absolute path to yourmcpproject directory.

{ "mcpServers": { "weather_server": { "command": "uv", "args": [ "run", "/mnt/d/Projects/_sandbox/mcp/mcp_weather.py" ], "cwd": "/mnt/d/Projects/_sandbox/mcp", "timeout": 10000 } } }

Once configured, when you rungemini, the CLI will automatically start yourmcp_weather.pyserver and make itsget_current_weathertool available to the Gemini model.

- Gemini CLI Configuration:https://github.com/google-gemini/gemini-cli/blob/main/docs/cli/configuration.md- For information on setting up MCP with the Gemini CLI.
- FastMCP:https://github.com/jlowin/fastmcp- The FastMCP library used for building MCP servers.

An AI-powered coding assistant that combines insights from Gemini, Stack Overflow, and Perplexity AI to help solve programming problems.