English · Español

datosgobdo-mcp

A Model Context Protocol server that exposes the Dominican Republic's open government data (datos.gob.do) as tools consumable by any AI assistant.

It turns the official Dominican open-data portal into a native integration for Claude Desktop, Claude Code, Cursor, ChatGPT Desktop or any MCP-compatible client. The model can search, read, analyze, and preview the 1,053+ datasets published by the country's 266 government institutions, all from within a conversation.

Official source. The canonical repository is alcastaro/datos.gob.do-MCP-server. The only official distributions are the PyPI package dominican-open-data-mcp and the MCP Registry entry io.github.alcastaro/datos.gob.do-MCP-server. Copies published elsewhere are not maintained by the author and may be outdated or modified — verify against this repository before installing.

📚 New here? Read the Tutorial — how the server works, how to use it, and how to build your own MCP server like it. (Español)

What problem does it solve?

datos.gob.do publishes thousands of CSV, XLSX, and JSON files with public data: payrolls, budgets, crime statistics, health indicators, electoral data, and more. Today that information is only accessible to people who know how to navigate the CKAN portal and download files manually.

This MCP closes that gap. Anyone can ask their assistant:

• "How much does the Judicial Branch spend on salaries?"
• "Compare FONDOMARENA's approved vs. executed budget over the last three years."
• "List the 10 institutions that publish the most data."
• "What columns does the Ministry of Interior's vehicle-theft dataset have?"

…and the model — without the user having to write code, navigate URLs, or download files — runs the actual queries against the portal, downloads the data, parses it, and analyzes it.

Who is it for?

• Data journalists wanting to explore official sources without writing scrapers.
• Researchers and academics needing programmatic access to Dominican government data.
• Transparency activists and civil society monitoring budget execution, procurement, and public administration.
• Developers and data scientists prototyping dashboards or analyses on public data.
• Public officials wanting to query what their own (or other) institutions already publish.
• Anyone with civic curiosity about how the government operates.

What is MCP?

Model Context Protocol is an open standard (created by Anthropic, adopted by OpenAI and others) that lets language models connect securely to external data sources and tools. An "MCP server" exposes a collection of typed functions; the model decides when to invoke them, with what arguments, and how to combine the results.

This project is an MCP server specialized in datos.gob.do.

What is datos.gob.do?

The official open-data portal of the Dominican government, operated by OGTIC (the country's IT and communications office). It runs on CKAN 2.11.3, the same open-data software used by portals like data.gov (USA), data.gov.uk, and many other Latin American governments.

As of May 2026 it contains approximately:

• 1,053 datasets published
• 266 organizations publishing (ministries, municipalities, autonomous agencies, etc.)
• 11 thematic categories (Economy, Health, Education, Public Management…)
• 852 tags

Each dataset bundles one or more "resources" (downloadable files) in formats such as CSV, XLSX, ODS, PDF, or JSON.

This MCP is inspired by datagouv-mcp (France), but datos.gob.

... View full README on GitHub