Fused MCP
A Python-based MCP server for data scientists to run Python code with a Claude client.
MCP servers allow LLMs like Claude to make HTTP requests, connecting them to APIs & executable code. We built this repo for ourselves & anyone working with data 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
-
Start by following our getting-started notebook
fused_mcp_agents.ipynb
in your favorite local IDE to get set up and then make your way to the more advanced notebook to make your own Agents & functions
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!
Here are a few common steps to debug the setup:
- Running
uv run main.py -h
should return something like this:
- You might need to pass global paths to some functions to the
Claude_Desktop_Config.json
. For example, by default we only passuv
:
{
"mcpServers": {
"qgis": {
"command": "uv",
"args": ["..."]
}
}
}
But you might need to pass the full path to uv
, which you can simply pass to common.generate_local_mcp_config
in the notebook:
# in fused_mcp_agents.ipynb
import shutil
common.generate_local_mcp_config(
config_path=PATH_TO_CLAUDE_CONFIG,
agents_list = ["get_current_time"],
repo_path= WORKING_DIR,
uv_path=shutil.which('uv'),
)
Which would create a config like this:
{
"mcpServers": {
"qgis": {
"command": "/Users/<YOUR_USERNAME>/.local/bin/uv",
"args": ["..."]
}
}
}
- If Claude runs without showing any connected tools, take a look at the MCP Docs for troubleshooting the Claude Desktop setup
Contribute
Feel free to open PRs to add your own UDFs to udfs/
so others can play around with them locally too!
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:
NOTE: You'll need an API key for Claude here as you won't use the Desktop App
-
Create an Anthropic Console Account
-
Create an Anthropic API Key
-
Create a
.env
:touch .env
-
Add your key as
ANTHROPIC_API_KEY
inside the.env
:# .env ANTHROPIC_API_KEY = "your-key-here"
-
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
Related Servers
Figma
Integrate Figma design data with AI coding tools using a local MCP server.
21st.dev Magic
Create crafted UI components inspired by the best 21st.dev design engineers.
Rakit UI AI
An intelligent tool for AI assistants to present multiple UI component designs for user selection.
Recraft AI
Generate and edit raster/vector images, vectorize, remove/replace backgrounds, and upscale using the Recraft AI API.
MCP Servers Collection
A collection of MCP servers for Claude Desktop, providing access to network tools, code linters, and Proxmox virtualization management.
A11y MCP Server
Perform accessibility audits on webpages using the axe-core engine to identify and help fix a11y issues.
PsiAnimator-MCP
A server for quantum physics simulation and animation, using QuTip for computations and Manim for visualizations.
Gemini Imagen 3.0
Generate high-quality images using Google's Imagen 3.0 model via the Gemini API.
SonarQube
Provides seamless integration with SonarQube Server or Cloud, and enables analysis of code snippets directly within the agent context
Jenkins Server MCP
A tool for interacting with Jenkins CI/CD servers, requiring environment variables for configuration.