convez.ai
MCP ServerDados & AnalyticsIntermediário
palewire

Datawrapper MCP Server

palewire/datawrapper-mcp

Crie gráficos Datawrapper conversando com IA

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP que integra Datawrapper com assistentes de IA, permitindo criar, editar, publicar e exportar gráficos através de conversa natural. Suporta múltiplos tipos de visualizações (barras, linhas, áreas, scatter, etc.) com controle total sobre dados e estilo.

Instalação

$npx convez-ai palewire/datawrapper-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
64
Forks
13
Acompanhando
4
Saúde
71%
Último commit
há 2 semanas
Versão
0.4.0
Issues abertas
16
Contribuidores
5

Casos de uso

  • Gerar visualizações de dados em tempo real durante análise
  • Automatizar criação de gráficos para relatórios e dashboards
  • Publicar e atualizar gráficos através de prompts naturais

Veredito

MCP bem implementado que democratiza a criação de gráficos ao permitir conversas naturais com IA. Ideal para analistas e jornalistas de dados que precisam gerar visualizações rapidamente sem sair da interface conversacional.

README

A tradução para o português deste README ainda está na fila.

PyPI MCP Registry Docker Hub

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.

Books chat chart

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

ToolDescription
list_chart_typesList available chart types with descriptions
get_chart_schemaGet the full configuration schema for a chart type
create_chartCreate a new chart with data and configuration
update_chartUpdate an existing chart's data or styling
publish_chartPublish a chart to make it publicly accessible
get_chartRetrieve a chart's configuration and metadata
delete_chartPermanently delete a chart
export_chart_pngExport 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

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, Cursor, VS Code Copilot, ChatGPT, OpenAI Codex) 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

ClientConfig fileTransport
Claude Desktopclaude_desktop_config.jsonstdio or streamable-http
Claude.aiManaged connectorstreamable-http
Claude Code.claude/settings.jsonstdio
VS Code Copilot.vscode/mcp.jsonstdio
Cursor.cursor/mcp.jsonstdio or streamable-http
ChatGPTDev Mode settingsstreamable-http only
OpenAI Codex~/.codex/config.tomlstdio
Ver o original no GitHub

Bom para

Relacionados