Mito AI MCP Server

This server enables LLMs to perform better data analysis and visualization, including best-in-class Excel-to-Python workflows.

Available Tools

• run_data_analyst - Run one-shot Mito AI analysis for notebook/spreadsheet workflows (Excel/CSV, cleaning/transforms, EDA, and Jupyter cell generation/edits).
  • Required arguments:
    • prompt (string): Natural-language instruction describing the analysis task.

Installation

The Mito AI MCP server works with any application that supports MCP. Below are setup instructions for a few popular tools: Cursor, VS Code, Claude Desktop. If yours isn’t listed, see Other Applications at the end.

[!TIP] To use the Mito AI MCP server the only requirement is uv. You can find installation instructions here.

Cursor

One-click install

For quick installation, use the one-click install:

Manual install

{
  "mcpServers": {
    "mito-ai": {
      "command": "uvx",
      "args": [
        "mito-ai-mcp"
      ]
    }
  }
}

VS Code

One-click install

For quick installation, use one of the one-click install buttons below:

Manual install

{
  "mcp": {
    "servers": {
      "mito-ai": {
        "command": "uvx",
        "args": ["mito-ai-mcp"]
      }
    }
  }
}

Claude Desktop

One-click install

1. Download the mcp bundle:

2. Double-click the .mcpb file. This should open Claude; follow the directions on screen.

Claude Code

In your terminal enter:

claude mcp add --transport stdio mito-ai -- uvx mito-ai-mcp

You should see a success message on submit. You can also enter claude from the terminal, and use the /mcp command to make sure the mito-ai MCP server is connected.

Other Applications

To set this up in another MCP-compatible app, find its MCP settings page in the docs.

Then add:

• Name: mito-ai
• Type: stdio
• Command: uvx
• Arguments: mito-ai-mcp

Development

Developers should consult the dev guide.