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Create an unpublished copy of a chart |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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。