# Vizro MCP server

> Build validated Vizro dashboards and Plotly charts from your data with help from your AI assistant.

- Listing: https://mcp.tc/i/vizro
- Connect: this is a local (stdio) server; install it on your machine (see Install). The listing link is a page, not an MCP endpoint.
- Type: local (stdio)
- Auth: no API key needed
- Category: [Data & Analytics](https://mcp.tc/c/analytics)
- Vendor: McKinsey (QuantumBlack)
- Homepage: <https://vizro.readthedocs.io/projects/vizro-mcp/>
- Repository: <https://github.com/mckinsey/vizro/tree/main/vizro-mcp>
- Package: pypi `vizro-mcp`

## About

Vizro-MCP works alongside an LLM to help create dashboards and charts with Vizro, the open-source low-code toolkit for data visualization apps built on Plotly and Dash. It is aimed at generating Vizro dashboard configurations and charts from your own data.

It runs locally over stdio, started with uvx vizro-mcp or from the mcp/vizro Docker image. No sign-in or API key is needed. The documentation states the server only reads data and never writes, deletes or modifies files on your machine. With Docker, mount your data folders into the container to use local files.

## What it can do

- Create Vizro dashboards with an LLM
- Generate Plotly charts from your data
- Work with local data files
- Run via uvx or Docker
- Works with Claude Desktop, Cursor and VS Code

## Example prompts

- "Build a Vizro dashboard from my sales.csv file"
- "Create a Plotly bar chart of revenue by region"
- "Add a filter and a second page to my Vizro dashboard"
- "Turn this dataset into an interactive dashboard"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport stdio vizro -- uvx vizro-mcp
```

2. Start Claude Code and type `/mcp`. **vizro** should show as connected.

Add `--scope user` to make it available in every project.

### Claude Desktop

1. Open **Settings → Developer → Edit Config**. It opens `claude_desktop_config.json`. Add:

`claude_desktop_config.json`:

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

2. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in `~/Library/Application Support/Claude/` on macOS and `%APPDATA%\Claude\` on Windows.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=vizro&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJ2aXpyby1tY3AiXX0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

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

Needs uv (Python) on your computer.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=vizro&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22vizro-mcp%22%5D%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"vizro","type":"stdio","command":"uvx","args":["vizro-mcp"]}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "vizro": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "vizro-mcp"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

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

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

### Codex

```bash
codex mcp add vizro -- uvx vizro-mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.vizro]
command = "uvx"
args = ["vizro-mcp"]
```

Needs uv (Python) on your computer.

### Gemini CLI

```bash
gemini mcp add vizro uvx vizro-mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients that start local servers accept this shape:

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

Zed puts servers under `context_servers` in its settings, with the same `command`, `args` and `env` fields.

Needs uv (Python) on your computer.

## Details

- Server version: 0.1.4
- Last checked: 2026-10-03
- Listed: 2026-10-03
- Updated: 2026-10-03

---
Source: https://mcp.tc/i/vizro (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report