Skip to main content
Glama
Sign In
Datos.gob.es-MCP

Datos.gob.es-MCP

by AnCode666
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Datos.gob.es-MCP. MCP integration with the Spanish Government Open Data Portal

en es

Datos.gob.es-mcp enables querying and analyzing over 90,000 public datasets available on the datos.gob.es portal directly from Claude AI and other compatible MCP clients using the Model Context Protocol (MCP).

This MCP server exposes tools for LLMs to search, filter, and access open data across multiple sectors.

Main features

  • Keyword search across dataset titles, descriptions and tags.

  • Thematic category filtering (environment, transportation, education, etc.)

  • Detailed metadata access for each dataset.

  • Available distributions listing (formats and access URLs)

  • Custom SPARQL queries execution against the official SPARQL endpoint.

Related MCP server: Opendata.cat MCP Server

Installation

Install via uv

Prerequisites

  • Python 3.10 or higher

  • uv package manager

uv Installation

First install uv, a modern Python package manager. Install from command line:

En MAC y Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

En Windows:

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

También se puede instalar con pip:

pip install uv

For more information about installing uv, visit the uv documentation.

Integration with clients like Claude for Desktop

Once uv is installed, you can use the MCP server with any compatible client like Claude Desktop. Configuration steps:

  1. Go to Claude > Settings > Developer > Edit Config > claude_desktop_config.json

  2. Add this configuration block under "mcpServers":

"datos_gob_es_mcp": {
    "command": "uvx",
    "args": [
        "datos_gob_es_mcp"
    ]
}

  1. If you have other MCP servers configured, separate them with commas ,

For other MCP-compatible clients like Cursor, CODEGPT or Roo Code, add the same configuration block to their respective MCP server settings.

Usage Examples

Once properly configured, you can request operations like:

- "Search for public transportation datasets in Madrid"
- "List latest datasets published by Barcelona City Council"
- "Show details for dataset with URI https://datos.gob.es/es/catalogo/l01330241-padron-de-vehiculos-ano-2023-autobuses"
---

Available Tools

10 tools
get_dataset_detailsC

Get detailed information about a specific dataset.

Args: dataset_uri: URI of the dataset to get details for

Inputs: dataset_uri (required).

get_dataset_distributionsC

Get available distributions (file formats) for a specific dataset.

Args: dataset_uri: URI of the dataset

Inputs: dataset_uri (required).

get_datasets_by_themeA

Get datasets belonging to a specific theme/category.

Args: theme_uri: URI of the theme limit: Maximum number of datasets to return (default: 10)

Inputs: theme_uri (required), limit.

get_latest_datasetsC

Get the most recently published datasets.

Args: limit: Maximum number of datasets to return (default: 10)

Inputs: limit.

get_publisher_datasetsB

Get datasets published by a specific organization.

Args: publisher_uri: URI of the publisher limit: Maximum number of datasets to return (default: 10)

Inputs: publisher_uri (required), limit.

list_datasetsB

List datasets available in the Spanish Government Open Data Portal.

Args: limit: Maximum number of datasets to return (default: 10)

Inputs: limit.

list_publishersB

List publishers (organizations) that publish datasets.

Args: limit: Maximum number of publishers to return (default: 10)

Inputs: limit.

list_themesA

List all themes/categories available in the data portal.

Inputs: no named parameters.

run_custom_sparqlC

Run a custom SPARQL query against the datos.gob.es endpoint.

Args: sparql_query: SPARQL query string (must be valid SPARQL)

Inputs: sparql_query (required).

search_datasetsA

Search datasets by keyword in title, description, and keywords/tags.

Args: keyword: Keyword to search for (case-insensitive). limit: Maximum number of datasets to return (default: 10).

Inputs: keyword (required), limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.6/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: listing, searching, filtering by theme/publisher, getting details/distributions, and running SPARQL queries. There is no overlap that could cause confusion.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case (e.g., list_datasets, get_dataset_details). The only exception, run_custom_sparql, still fits the verb_noun style and is clear.

    Tool Count5/5

    10 tools is well-scoped for the domain of accessing open government data, covering all essential operations without being excessive or too few.

    Completeness4/5

    The tool set covers dataset discovery, filtering, details, and distributions, plus listing publishers and themes. A custom SPARQL endpoint adds flexibility. Minor gaps include no drill-down into publisher/theme details, but core workflows are supported.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • Opendata.cat MCP Server

      xaviviro
      A
      license
      A
      quality
      C
      maintenance
      Connects LLMs to over 2,850 datasets from 13 Catalan and Spanish open data portals, enabling natural language search and real-time queries of public data.
      8
      77 npm
      22
      MIT

    • dados-pt

      pipeworx-io
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables querying Portugal's national open data portal (dados.gov.pt) through natural language.
      318 npm
      MIT

    • datos-gob-es

      pipeworx-io
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to search and retrieve datasets, publishers, and themes from Spain's national open-data catalogue through keyless MCP tools or HTTP endpoints.
      128 npm
      MIT