Datawrapper MCP
Enables creating, managing, and publishing Datawrapper charts.
README
Datawrapper MCP
A remote Model Context Protocol server for creating and managing Datawrapper visualizations.
What it does
The server exposes seven tools:
| Tool | Purpose |
|---|---|
list_charts |
List charts with pagination |
get_chart |
Retrieve chart configuration and links |
create_chart |
Create a chart and optionally upload data |
update_chart_data |
Replace data using CSV or structured rows |
update_chart_metadata |
Update title, description, byline, source, and notes |
publish_chart |
Publish or republish a chart |
duplicate_chart |
Create an unpublished copy of a chart |
No delete tool is included.
Architecture
- Next.js App Router
- Vercel
mcp-handler - Streamable HTTP transport
- Datawrapper API v3
- MCP endpoint:
/api/mcp - Health endpoint:
/api/health
Environment variables
Copy .env.example to .env.local.
cp .env.example .env.local
| Variable | Required | Purpose |
|---|---|---|
DATAWRAPPER_API_TOKEN |
Yes | Personal Datawrapper API token |
MCP_ACCESS_TOKEN |
No | Requires the same bearer token on MCP requests |
DATAWRAPPER_API_BASE_URL |
No | Defaults to https://api.datawrapper.de/v3 |
Create the Datawrapper token in the Datawrapper account settings. For the complete toolset, grant chart:read and chart:write. Grant folder permissions only when creating charts inside folders.
Never commit real tokens.
Local development
npm install
npm test
npm run typecheck
npm run dev
The MCP endpoint will be:
http://localhost:3000/api/mcp
The health check will be:
http://localhost:3000/api/health
Test the server using the MCP Inspector:
npx @modelcontextprotocol/inspector@latest
Select Streamable HTTP and connect to http://localhost:3000/api/mcp.
Deploy to Vercel
- Import this GitHub repository into Vercel.
- Add
DATAWRAPPER_API_TOKENto Production, Preview, and Development as needed. - Optionally add
MCP_ACCESS_TOKEN. - Deploy.
- Open
/api/health. - Connect an MCP client to
https://<deployment-domain>/api/mcp.
MCP client configuration
For clients that accept a Streamable HTTP URL:
{
"mcpServers": {
"datawrapper": {
"url": "https://<deployment-domain>/api/mcp"
}
}
}
When MCP_ACCESS_TOKEN is configured, the client must support sending:
Authorization: Bearer <MCP_ACCESS_TOKEN>
Some hosted chat clients require OAuth rather than a static header. In that case, add an OAuth authorization layer before using this server with sensitive production data.
Example requests
Create a chart from structured rows:
{
"title": "Revenue by market",
"type": "d3-bars",
"rows": [
{ "Market": "UAE", "Revenue": 120 },
{ "Market": "UK", "Revenue": 85 }
]
}
Update attribution:
{
"chartId": "abc12",
"sourceName": "Company filings",
"sourceUrl": "https://example.com/source",
"byline": "Strategy team"
}
Security notes
- Datawrapper credentials remain server-side.
- Health checks disclose only whether variables are configured.
- Upstream errors are sanitized and never include the API token.
- Publishing is an explicit separate tool.
- New and duplicated charts remain unpublished until
publish_chartis called.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.