Datawrapper Charts
A Model Context Protocol (MCP) server and app for creating Datawrapper charts using AI assistants.
What is Datawrapper Charts?
Datawrapper Charts is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server and app for creating datawrapper charts using ai assistants.
A Model Context Protocol (MCP) server and app for creating Datawrapper charts using AI assistants.
This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol (MCP) server and app for creating D
Use Cases
Maintainer
Works with
Installation
NPM
npx -y datawrapper-mcpPIP
pip install datawrapper-mcpManual Installation
npx -y datawrapper-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Datawrapper Charts
Datawrapper MCP Server connects AI assistants to the Datawrapper charting platform, enabling conversational creation, updating, styling, and publishing of publication-ready charts. It exposes tools for every stage of the chart lifecycle — from listing available chart types and schemas to creating charts with data, publishing them publicly, exporting PNG images, and deleting drafts. Data journalists, analysts, and content teams use it to go from raw data to a published, embeddable chart without leaving their AI chat interface.
Prerequisites
- A Datawrapper account (sign up free at datawrapper.de/signup/)
- A Datawrapper API token from app.datawrapper.de/account/api-tokens
- Python 3.10 or higher (for running via uvx or pip)
- An MCP-compatible client: Claude Desktop, Claude Code, Cursor, VS Code Copilot, or ChatGPT
Create a Datawrapper API token
Log in to Datawrapper, go to Account > API Tokens, and create a new token with read and write permissions. Copy the token — you will need it in your MCP configuration.
Configure Claude Desktop with uvx
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows). Using uvx is the recommended approach as it runs in an isolated environment.
{
"mcpServers": {
"datawrapper": {
"command": "uvx",
"args": ["datawrapper-mcp"],
"env": {
"DATAWRAPPER_ACCESS_TOKEN": "your-token-here"
}
}
}
}Alternatively, install via pip
If you prefer a persistent installation or uvx is not available, install the package with pip.
pip install datawrapper-mcpConfigure with pip-installed binary
After pip installation, update your MCP config to run the installed binary directly.
{
"mcpServers": {
"datawrapper": {
"command": "datawrapper-mcp",
"args": [],
"env": {
"DATAWRAPPER_ACCESS_TOKEN": "your-token-here"
}
}
}
}Restart Claude Desktop and test
Restart Claude Desktop. Ask Claude to list available chart types to confirm the server is connected and your API token is valid.
Datawrapper Charts Examples
Client configuration (Claude Desktop with uvx)
Recommended configuration using uvx with your Datawrapper API token set as an environment variable.
{
"mcpServers": {
"datawrapper": {
"command": "uvx",
"args": ["datawrapper-mcp"],
"env": {
"DATAWRAPPER_ACCESS_TOKEN": "your-datawrapper-api-token"
}
}
}
}Prompts to try
Use these prompts to create and manage Datawrapper charts conversationally.
- "Create a Datawrapper bar chart with this data: Category A: 45, Category B: 72, Category C: 38."
- "Publish the chart with ID abc123 and give me the public URL."
- "Update the chart abc123 to add a 2024 data point: 17.5°C."
- "Make the line color on chart abc123 dodger blue."
- "Export chart abc123 as a PNG image."
- "List all available chart types with their descriptions."
- "What configuration options are available for a scatter chart?"Troubleshooting Datawrapper Charts
API calls return 401 Unauthorized or 403 Forbidden
Verify that your DATAWRAPPER_ACCESS_TOKEN is correct and has not expired. Go to app.datawrapper.de/account/api-tokens and regenerate the token if needed. Ensure the token has both read and write scopes enabled.
uvx command not found when starting the server
Install uv first: run 'pip install uv' or follow the installation instructions at docs.astral.sh/uv. Alternatively, use the pip-installed binary approach: 'pip install datawrapper-mcp' and use 'datawrapper-mcp' as the command in your config.
Published chart URL returns a 404 or the chart appears empty
Ensure you called publish_chart after create_chart — charts are drafts by default and are not publicly accessible until published. If the chart appears empty, check that the data you provided matches the expected format for the chart type by calling get_chart_schema first.
Frequently Asked Questions about Datawrapper Charts
What is Datawrapper Charts?
Datawrapper Charts is a Model Context Protocol (MCP) server that model context protocol (mcp) server and app for creating datawrapper charts using ai assistants. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Datawrapper Charts?
Install via npm with the command: npx -y datawrapper-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Datawrapper Charts?
Datawrapper Charts works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Datawrapper Charts free to use?
Yes, Datawrapper Charts is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Datawrapper Charts Alternatives — Similar Analytics Servers
Looking for alternatives to Datawrapper Charts? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.
OpenMetadata
★ 14.0kOpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Superset
★ 10.9kAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
Horizon
★ 4.4k📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
MCP Server Chart
★ 4.1kEnables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations
Muapi CLI
★ 997Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
★ 907Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien
Browse More Analytics MCP Servers
Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Datawrapper Charts in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Datawrapper Charts?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.