Datawrapper
Wraps the Datawrapper API so you can create, update, and publish charts through conversation. You get eight tools covering the full lifecycle: list available chart types, fetch configuration schemas, create charts from data, update styling, publish to public URLs, and export PNGs. Supports bar, line, area, scatter, and stacked variants. Authentication works three ways: environment variable for local stdio, Authorization header for hosted deployments, or direct token argument per call. Useful when you're iterating on data visualizations and want to skip the web interface. Built on the datawrapper Python library and works with Claude Desktop, VS Code Copilot, Cursor, and ChatGPT.
- GitHub stars
- 61
- tools
- 8
- auth
- Secret needed
- transport
- STDIO
- env var
- 1
- last updated
- Sep 13, 2026
Tools
8 toolsPublic tool metadata for what this MCP can expose to an agent.
list_chart_typesList available chart types with descriptions
List available chart types with descriptions
No parameter schema in public metadata yet.
get_chart_schemaGet the full configuration schema for a chart type
Get the full configuration schema for a chart type
No parameter schema in public metadata yet.
create_chartCreate a new chart with data and configuration
Create a new chart with data and configuration
No parameter schema in public metadata yet.
update_chartUpdate an existing chart's data or styling
Update an existing chart's data or styling
No parameter schema in public metadata yet.
publish_chartPublish a chart to make it publicly accessible
Publish a chart to make it publicly accessible
No parameter schema in public metadata yet.
get_chartRetrieve a chart's configuration and metadata
Retrieve a chart's configuration and metadata
No parameter schema in public metadata yet.
delete_chartPermanently delete a chart
Permanently delete a chart
No parameter schema in public metadata yet.
export_chart_pngExport a chart as a PNG image
Export a chart as a PNG image
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
DATAWRAPPER_ACCESS_TOKEN*secretDatawrapper API Access Token
Readme
A Model Context Protocol (MCP) server and app for creating Datawrapper charts using AI assistants. Built on the datawrapper Python library.
Status: early and experimental. This project — including its Claude Code/Desktop plugin and marketplace listing — is under active development, and behavior can change between releases. In particular, the plugin/marketplace install path has known gaps (see issue #78) — don't treat it yet as a finished, zero-maintenance install path for a wider rollout.
Example Usage
You can provide a data file and simply ask for the chart you want. The draft will soon appear in the panel.
Details
- Repository
- github.com/palewire/datawrapper-mcp
- Package
datawrapper-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active