Vizro MCP server

Vizro-MCP is a Model Context Protocol (MCP) server that integrates with large language models (LLMs) to help you create Vizro dashboards and charts. This tool enhances your ability to generate data visualizations by connecting your preferred LLM application with Vizro's dashboard creation capabilities.

Installation Options

You can set up Vizro-MCP using either uv or Docker, depending on your preference. The server works best with Claude Desktop, Cursor, or VS Code, though it's compatible with most LLM products that support MCP server configuration.

Prerequisites

Before installing Vizro-MCP, you'll need:

• An LLM application (like Claude Desktop, Cursor, or VS Code)
• Either uv or Docker installed on your system

Installation with uv

1. Verify that uv is installed by opening a terminal and typing:

uv

2. Find the path to uvx with:

which uv

3. Configure your LLM application by adding the following to its MCP server configuration JSON file (replace the placeholder path with your actual path to uv):

{
  "mcpServers": {
    "vizro-mcp": {
      "command": "/placeholder-path/uvx",
      "args": [
        "vizro-mcp"
      ]
    }
  }
}

Quick Installation Links for uv

• For Cursor: Install with UVX in Cursor
• For VS Code: Install with UVX in VS Code

Installation with Docker

1. Add the following to your LLM application's MCP server configuration JSON file:

{
  "mcpServers": {
    "vizro-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "mcp/vizro"
      ]
    }
  }
}

Using Local Data with Docker

To use local data with the Docker installation, mount your data directories or files by extending the configuration:

{
  "mcpServers": {
    "vizro-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--mount",
        "type=bind,src=</absolute/path/to/allowed/dir>,dst=</absolute/path/to/allowed/dir>",
        "--mount",
        "type=bind,src=</absolute/path/to/data.csv>,dst=</absolute/path/to/data.csv>",
        "mcp/vizro"
      ]
    }
  }
}

Replace </absolute/path/to/allowed/dir> or </absolute/path/to/data.csv> with the absolute path to your data on your machine.

Quick Installation Links for Docker

• For Cursor: Install with Docker in Cursor
• For VS Code: Install with Docker in VS Code

Usage Tips

• For optimal performance, use the claude-4-sonnet model or another high-performing model of your choice
• Avoid using the auto setting for model selection as it may lead to inconsistent results
• When using Docker with local data, ensure you properly mount your data directories
• The server only reads data and never writes, deletes, or modifies any data on your machine

After installation, you can prompt your LLM to create Vizro dashboards and charts based on your data. The Vizro-MCP server will help the LLM understand your data and generate appropriate visualization code.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "vizro-mcp" '{"command":"uvx","args":["vizro-mcp"]}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "vizro-mcp": {
            "command": "uvx",
            "args": [
                "vizro-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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect