Datawrapper Mcp

What is Datawrapper Mcp about?

Datawrapper Mcp provides an MCP server and client‑side app that lets AI assistants (e.g., Claude, OpenAI Codex) manage Datawrapper charts via simple chat commands. Users can supply raw data, request specific chart types, adjust styling, and obtain URLs or PNG images, all without writing API calls manually.

How to use Datawrapper Mcp?

1. Obtain a Datawrapper API token from your Datawrapper account.
2. Configure the MCP server (see the serverConfig section) and start it.
3. Add the token to the server environment (DATAWRAPPER_ACCESS_TOKEN) or send it in the Authorization header for hosted instances.
4. Interact via an MCP‑compatible client (Claude Desktop, Claude.ai, VS Code Copilot, Cursor, ChatGPT, etc.) by sending natural‑language prompts such as:
   • “Create a line chart showing temperature trends with this data …”
   • “Publish it.”
   • “Update chart with new data for 2024: 17.2°C.”
   • “Show me the PNG.”
5. The assistant calls the appropriate tool (create_chart, update_chart, publish_chart, export_chart_png, etc.) and returns the result.

Key features of Datawrapper Mcp

• Toolset exposing the full Datawrapper API: list chart types, retrieve schemas, create, update, publish, delete, and export charts as PNG.
• Natural‑language driven workflow: users describe the desired chart and modifications; the assistant translates them into API calls.
• Multi‑client support: works with Claude Desktop, Claude.ai, VS Code Copilot, Cursor, ChatGPT, OpenAI Codex, OpenClaw, and Kubernetes deployments.
• Secure token handling: token can be supplied via environment variable, HTTP Authorization header, or explicit access_token argument, with precedence rules.
• Docker image available for easy deployment.

Use cases of Datawrapper Mcp

• Journalists and data‑driven storytellers rapidly generate visualizations while drafting articles.
• Data analysts automate repetitive chart updates (e.g., monthly KPI dashboards) via chat commands.
• Education platforms let students explore data visualization concepts interactively.
• Newsrooms integrate chart creation directly into editorial workflows without manual API coding.

FAQ from the Datawrapper Mcp

• Do I need a Datawrapper account? Yes, an account and an API token are required.
• Can I use my own token on a hosted server? Absolutely – send it in the Authorization: Bearer <token> header or as the access_token argument.
• Which chart types are supported? Bar, line, area, arrow, column, multiple column, scatter, stacked bar (use list_chart_types for full descriptions).
• How is authentication handled? The server first checks the request header, then the access_token argument, and finally falls back to the DATAWRAPPER_ACCESS_TOKEN environment variable.
• Is there a Docker image? Yes, pull palewire/datawrapper-mcp from Docker Hub.
• What Python version is required? Python 3.10 or newer.
• Can I delete a chart via chat? Yes, use the delete_chart tool with the chart ID.

A Model Context Protocol (MCP) server and app for creating Datawrapper charts using AI assistants. Built on the datawrapper Python library.

Example Usage

You can provide a data file and simply ask for the chart you want. The draft will soon appear in the panel.

Here's a more complete example showing how to create, publish, update, and display a chart by chatting with the assistant:

"Create a datawrapper line chart showing temperature trends with this data:
2020, 15.5
2021, 16.0
2022, 16.5
2023, 17.0"
# The assistant creates the chart and returns the chart ID, e.g., "abc123"

"Publish it."
# The assistant publishes it and returns the public URL

"Update chart with new data for 2024: 17.2°C"
# The assistant updates the chart with the new data point

"Make the line color dodger blue."
# The assistant updates the chart configuration to set the line color

"Show me the editor URL."
# The assistant returns the Datawrapper editor URL where you can view/edit the chart

"Show me the PNG."
# The assistant embeds the PNG image of the chart in its contained response.

"Suggest five ways to improve the chart."
# See what happens!

Tools

Tool	Description
list_chart_types	List available chart types with descriptions
get_chart_schema	Get the full configuration schema for a chart type
create_chart	Create a new chart with data and configuration
update_chart	Update an existing chart's data or styling
publish_chart	Publish a chart to make it publicly accessible
get_chart	Retrieve a chart's configuration and metadata
delete_chart	Permanently delete a chart
export_chart_png	Export a chart as a PNG image

Chart Types

bar, line, area, arrow, column, multiple column, scatter, stacked bar

Use list_chart_types to see descriptions, then get_chart_schema to explore configuration options for any type.

Getting Started

Requirements

• A Datawrapper account (sign up at https://datawrapper.de/signup/)
• An MCP client such as Claude or OpenAI Codex
• Python 3.10 or higher

Get Your API Token

1. Go to https://app.datawrapper.de/account/api-tokens
2. Create a new API token
3. Add it to your MCP configuration as shown in the installation guide

Quick Start (Claude Code)

{
  "mcpServers": {
    "datawrapper": {
      "command": "uvx",
      "args": ["datawrapper-mcp"],
      "env": {
        "DATAWRAPPER_ACCESS_TOKEN": "your-token-here"
      }
    }
  }
}

For other clients (Claude Desktop, Claude.ai, Cursor, VS Code Copilot, ChatGPT, OpenAI Codex, OpenClaw) and Kubernetes deployment, see the installation guide.

Using Your Own Token (Hosted Deployments)

When connecting to a hosted instance of the server over HTTP, you can authenticate with your own Datawrapper API token by sending it in the Authorization header:

Authorization: Bearer <your-datawrapper-api-token>

This ensures charts are created under your account instead of the server operator's. The token is read from the header automatically — no need to include it in every tool call.

You can also pass access_token directly as a tool argument, which takes precedence over the header. When neither is provided, the server falls back to its DATAWRAPPER_ACCESS_TOKEN environment variable.

Supported Clients

Client	Config file	Transport
Claude Desktop	claude_desktop_config.json	stdio or streamable-http
Claude.ai	Personal or org connector	streamable-http
Claude Code	.mcp.json	stdio
VS Code Copilot	.vscode/mcp.json	stdio
Cursor	.cursor/mcp.json	stdio or streamable-http
ChatGPT	Dev Mode settings	streamable-http only
OpenAI Codex	~/.codex/config.toml	stdio
OpenClaw	openclaw.json	stdio