Fused MCP Agents: Setting up MCP Servers for Data Scientists

MCP servers allow Claude & other LLMs to make HTTP requests, connecting them to APIs & executable code. We built this repo for ourselves & other data scientists to easily pass any Python code directly to your own desktop Claude app.

This repo offers a simple step-by-step notebook workflow to setup MCP Servers with Claude's Desktop App, all in Python built on top of Fused User Defined Functions (UDFs).

Requirements

• Python 3.11
• Latest Claude Desktop app installed (MacOS & Windows)

If you're on Linux, the desktop app isn't available so we've made a simple client you can use to have it running locally too!

You do not need a Fused account to do any of this! All of this will be running on your local machine

Installation

• Clone this repo in any local directory, and navigate to the repo:

  git clone https://github.com/fusedio/fused-mcp.git
  cd fused-mcp/

• Install uv if you don't have it:

  Macos / Linux:

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

  Windows:

  powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
  

• Test out the client by asking for its info:

  uv run main.py -h

This should give you something like:

• Open the fused_mcp_agents.ipynb notebook in your favorite local IDE & follow instructions from there.

Repository structure

This repo is build on top of MCP Server & Fused UDFs which are Python functions that can be run from anywhere.

Support & Community

Feel free to join our Discord server if you want some help getting unblocked!

Contribute

Feel free to open PRs to add your own UDFs to udfs/ so others can play around with them locally to!

Using a local Claude client (without Claude Desktop app)

If you are unable to install the Claude Desktop app (e.g., on Linux), we provide a small example local client interface to use Claude with the MCP server configured in this repo:

• This workflow requires an API key Claude as an environment variable. For example, add a .env file in this repo with an ANTHROPIC_API_KEY entry.

• Start the MCP server:

  uv run main.py --agent get_current_time

• In another terminal session, start the local client, pointing to the address of the server:

  uv run client.py http://localhost:8080/sse