Vizro MCP

Name: Vizro MCP
Author: mckinsey

@mckinsey

Repository

About Vizro MCP

MCP server to help with chat and dashboard creation.

#design #dashboard #viz #charts #dash #plotly #vizro

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

Get instructions for creating a Vizro chart or dashboard. Call FIRST when asked to create Vizro things. Must be ALWAYS called FIRST with advanced_mode=False, then call again with advanced_mode=True if the JSON config does not suffice anymore. Args: user_plan: The type of Vizro thing the user wants to create user_host: The host the user is using, if "ide" you can use the IDE/editor to run python code advanced_mode: Only call if you need to use custom CSS, custom components or custom actions. No need to call this with advanced_mode=True if you need advanced charts, use `custom_charts` in the `validate_dashboard_config` tool instead. Returns: Instructions for creating a Vizro chart or dashboard

Get the JSON schema for the specified Vizro model. Args: model_name: Name of the Vizro model to get schema for (e.g., 'Card', 'Dashboard', 'Page') Returns: JSON schema of the requested Vizro model

If user provides no data, use this tool to get sample data information. Use the following data for the below purposes: - iris: mostly numerical with one categorical column, good for scatter, histogram, boxplot, etc. - tips: contains mix of numerical and categorical columns, good for bar, pie, etc. - stocks: stock prices, good for line, scatter, generally things that change over time - gapminder: demographic data, good for line, scatter, generally things with maps or many categories Args: data_name: Name of the dataset to get sample data for Returns: Data info object containing information about the dataset.

Use to understand local or remote data files. Must be called with absolute paths or URLs. Supported formats: - CSV (.csv) - JSON (.json) - HTML (.html, .htm) - Excel (.xls, .xlsx) - OpenDocument Spreadsheet (.ods) - Parquet (.parquet) Args: path_or_url: Absolute (important!) local file path or URL to a data file Returns: DataAnalysisResults object containing DataFrame information and metadata

Validate Vizro model configuration. Run ALWAYS when you have a complete dashboard configuration. If successful, the tool will return the python code and, if it is a remote file, the py.cafe link to the chart. The PyCafe link will be automatically opened in your default browser if auto_open is True. Args: dashboard_config: Either a JSON string or a dictionary representing a Vizro dashboard model configuration data_infos: List of DFMetaData objects containing information about the data files custom_charts: List of ChartPlan objects containing information about the custom charts in the dashboard auto_open: Whether to automatically open the PyCafe link in a browser Returns: ValidationResults object with status and dashboard details

Validate the chart code created by the user and optionally open the PyCafe link in a browser. Args: chart_config: A ChartPlan object with the chart configuration data_info: Metadata for the dataset to be used in the chart auto_open: Whether to automatically open the PyCafe link in a browser Returns: ValidationResults object with status and dashboard details

Overview

What is Vizro MCP?

Vizro MCP is an open-source Python-based low-code toolkit for building high-quality data visualization apps quickly and easily, without needing advanced engineering or visual design expertise, and then customizing and deploying them to production at scale.

How to use Vizro MCP?

Install the package with pip install vizro, then configure dashboards using a few lines of simple low-code configuration (via Pydantic models, JSON, YAML, or Python dictionaries). See the get started documentation for creating your first dashboard.

Key features of Vizro MCP

Build beautiful multi-page apps with low-code configuration.
In-built visual design best practices.
Powered by trusted open-source packages: Plotly, Dash, Pydantic.
Extendable with Python, JavaScript, HTML, and CSS code.
Rapid prototyping to production deployment.
Includes Vizro-AI for generating charts/dashboards via LLMs.

Use cases of Vizro MCP

Create professional data visualization dashboards in minutes.
Combine the speed of low-code with production-grade capabilities.
Prototype quickly and scale to production with minimal effort.
Use plain English to generate interactive charts and dashboards via Vizro-AI.

FAQ from Vizro MCP

What is Vizro MCP?

Vizro MCP is a low-code Python toolkit for building data visualization apps. It simplifies dashboard creation with configuration files and comes with built-in design best practices.

How do I install Vizro MCP?

Install vizro via pip: pip install vizro. See the installation guide for more details.

Why should I use Vizro MCP over other BI tools?

It offers the simplicity of low-code, the power of open-source Python packages (Plotly, Dash, Pydantic), full customization with code, and production scalability—all without requiring advanced engineering or design skills.