Modal (Serverless Python) MCP server

Integrates with Modal's serverless platform to deploy and execute Python scripts in the cloud, enabling efficient distributed computing and data processing.
Back to servers
Provider
Flux159
Release date
Dec 11, 2024
Language
Python
Stats
4 stars

This server implements the Model Context Protocol (MCP) for Modal, enabling you to deploy Python scripts directly to Modal's cloud platform from within your Claude desktop application.

Installation

Prerequisites

Before setting up the MCP Modal server, ensure that Modal is properly installed and configured:

pip install modal
python3 -m modal setup

Setting Up the Server

Configure the MCP server in your Claude desktop application by updating your configuration to include both the Modal server and the filesystem server:

{
   "mcpServers": {
        "mcp-server-modal": {
            "command": "uv",
            "args": [
                "--directory",
                "/path/to/mcp-server-modal",
                "run",
                "modal-server"
            ]
        },
        "filesystem": {
            "command": "npx",
            "args": [
                "-y",
                "@modelcontextprotocol/server-filesystem",
                "/Users/user/Desktop/",
                "/path/to/other/dir"
            ]
        }
   }
}

Make sure to replace /path/to/mcp-server-modal with the actual path to where you've stored the MCP Modal server, and adjust the filesystem paths accordingly.

Usage

The MCP Modal server allows you to seamlessly deploy Python code to Modal directly from your Claude interactions:

  1. In Claude, write or request a Python script that you want to deploy
  2. Ask Claude to create a Modal application and deploy it for you
  3. After code generation completes, Claude will provide a link to your deployed Modal application

You can then access your deployed application via the provided link, test its functionality, and share it with others.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later