Fused UDF

by fusedio

23 stars

Not rated

GitHub

About

Python-based framework for connecting Claude and other LLMs to executable Python code through User Defined Functions, enabling data scientists to extend their models with custom Python capabilities.

Details

Author: fusedio
Repository: fusedio/fused-mcp
GitHub stars: 23
License: MIT License
Categories: Developer Tools, Other, AI, Productivity, Design, Infrastructure, Project Management, Frontend

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name Fused UDF

Command (node, npx, python, etc.) uv
Arguments
- Argument 1 ...
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {
                "ANTHROPIC_API_KEY": "your-key-here"
            },
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {
                "ANTHROPIC_API_KEY": "your-key-here"
            },
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {
                "ANTHROPIC_API_KEY": "your-key-here"
            },
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {
                "ANTHROPIC_API_KEY": "your-key-here"
            },
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

JSON

{
    "mcpServers": {
        "fused udf": {
            "env": {
                "ANTHROPIC_API_KEY": "your-key-here"
            },
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

From the repository

- 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

Notebook

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "fused udf": {
            "env": {},
            "args": [
                "..."
            ],
            "command": "uv"
        }
    }
}

Linux

{
    "env": {
        "ANTHROPIC_API_KEY": "your-key-here"
    },
    "args": [
        "..."
    ],
    "command": "uv"
}

Macos

{
    "env": [],
    "args": [
        "..."
    ],
    "command": "uv"
}

Windows

{
    "env": [],
    "args": [
        "..."
    ],
    "command": "uv"
}

<h1 align="center">
Fused MCP Agents: Setting up MCP Servers for Data
</h1>

<p align="center">
<a
href="https://docs.fused.io/"
target="_blank"
><b>Documentation</b></a>   🌪️   
<a
href="https://docs.fused.io/blog/announcing-fused-ai-builder/"
target="_blank"
><b>Read the announcement</b>
</a>   🔥   
<a
href="https://discord.com/invite/Eryz9P2DeY"
target="_blank"
>
<b>Join Discord</b>
</a>
</p>

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).

Demo once setup

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

Notebook

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:

uv helper output function

- You might need to pass global paths to some functions to the Claude_Desktop_Config.json. For example, by default we only pass uv:

{
    "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:

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

Linux

Macos

Windows

Requirements

Installation

Repository structure

Support & Community

Contribute

Using a local Claude client (without Claude Desktop app)

Install

More like this

Sequential Thinking

Sentry

Github

Filesystem

EverArt

Google Drive