try_fastmcp
@iAbdelRahim
chat with a llm having access to a mcp server.
Overview
What is try_fastmcp?
try_fastmcp is a Python application that uses the FastMCP library to create an MCP server. It integrates with the OpenAI API and provides tools for dataset retrieval, news search, and mathematical operations, as well as a greeting resource. It is intended for developers who need a lightweight MCP server with these capabilities.
How to use try_fastmcp?
Clone the repository, create and activate a virtual environment, install dependencies with pip install -r requirements.txt, and set your OpenAI API key in the .env file. Run the server with python server.py and the client with streamlit run client.py.
Key features of try_fastmcp?
- Retrieve all public datasets from data.gouv.ci catalog.
- Fetch news articles based on user queries.
- Perform 13 mathematical operations (add, subtract, multiply, divide, etc.)
- Generate personalized greetings via a resource endpoint.
- Uses FastMCP library and OpenAI API.
Use cases of try_fastmcp?
- Automating dataset discovery from a government open data portal.
- Performing quick arithmetic or scientific calculations through an MCP tool.
- Integrating news search into a larger AI‑powered workflow.
- Demonstrating how to build and run a FastMCP server with Python.
FAQ from try_fastmcp
What Python version is required?
Python 3.6 or higher is required.
How do I set the OpenAI API key?
Rename the .env.example file to .env and fill in your OPENAI_API_KEY.
What tools does the server provide?
It provides get_all_datasets, websearch_newssearch, and 11 math tools (add, subtract, multiply, divide, power, sqrt, cbrt, factorial, log, remainder, sin, cos, tan).
How do I run the client?
Execute streamlit run client.py in the activated virtual environment.
What is the greeting resource?
The resource greeting://{name} returns a personalized greeting for the given name.
