Opendata Cat is a remote MCP server that gives an AI agent 8 tools, among them get_dataset_info, list_categories, list_dataset_fields. It answers at https://opendata.cat/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
15 Catalan portals + radio archive: gov, INE/REE/CNMC, CORA, Catalònica, radioteca.cat.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
get_dataset_info | Get complete metadata for a dataset: fields with types and descriptions, API endpoint, license, available formats and last update. Call after search_datasets to get full details of a specific dataset. Inputs: dataset_id |
list_categories | List all dataset categories and themes with counts per portal. Great first step to discover what data types are available before searching with search_datasets. Returns total datasets, count per portal and category list with counts. No para |
list_dataset_fields | List fields of a dataset with name, data type and description. Call before query_dataset to know which fields and filters are available. Inputs: dataset_id |
list_portals | List all 13 indexed open data portals with dataset counts. Catalan portals (Generalitat, Barcelona, Diba, AOC, Reus, Girona, FGC, Idescat, Renfe) + Spanish national sources with Catalonia focus (INE statistics, REE energy, SEPE employment, |
query_dataset | Query real data from a dataset. Check instructions for featured dataset_ids and NOTES section for common filter patterns (municipal budgets, contracts, weather, energy, fuel prices). Inputs: dataset_id, filters, search, limit, offset |
related_datasets | Find related datasets from OTHER portals. Great for discovering complementary data: if you're looking at air quality from Generalitat, it may suggest traffic data from Barcelona or emissions from AOC. Relations are computed by thematic simi Inputs: dataset_id |
search_datasets | Search datasets by free text. IMPORTANT: check server instructions first — many common queries have a direct dataset_id you can use with query_dataset without searching. Only use search_datasets when you don't know which dataset you need. Inputs: query, portal, category, limit |
search_radioteca | Search radio shows, episodes and people indexed at radioteca.cat (Catalan radio archive, ~485K documents from Catalunya Ràdio, RAC1, Catalunya Música, iCat, Catalunya Informació, RTVE, Cadena SER, ara.cat). Searches across episode titles, d Inputs: query, publisher, year, type, limit, offset |
Every block below points at https://opendata.cat/api/mcp. Pick your client and copy.
claude mcp add --transport http opendata-cat https://opendata.cat/api/mcp
{
"mcpServers": {
"opendata-cat": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://opendata.cat/api/mcp"]
}
}
}{
"mcpServers": {
"opendata-cat": {
"url": "https://opendata.cat/api/mcp"
}
}
}{
"servers": {
"opendata-cat": {
"type": "http",
"url": "https://opendata.cat/api/mcp"
}
}
}{
"context_servers": {
"opendata-cat": {
"url": "https://opendata.cat/api/mcp"
}
}
}{
"mcpServers": {
"opendata-cat": {
"serverUrl": "https://opendata.cat/api/mcp"
}
}
}{
"mcpServers": {
"opendata-cat": {
"url": "https://opendata.cat/api/mcp"
}
}
}name: Opendata Cat
version: 0.0.1
schema: v1
mcpServers:
- name: Opendata Cat
type: streamable-http
url: https://opendata.cat/api/mcp{
"mcpServers": {
"opendata-cat": {
"httpUrl": "https://opendata.cat/api/mcp"
}
}
}{
"mcpServers": {
"opendata-cat": {
"type": "http",
"url": "https://opendata.cat/api/mcp"
}
}
}{
"mcpServers": {
"opendata-cat": {
"url": "https://opendata.cat/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fopendata.cat%2Fapi%2Fmcp&type=streamable_http&id=opendata-cat&name=Opendata%20Cat
It answered our last check on 24 October 2026 in 107 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
8, as returned by the server's own tools/list on 22 September 2026: get_dataset_info, list_categories, list_dataset_fields, list_portals, query_dataset, related_datasets, search_datasets, search_radioteca.
It answered our last check on 24 October 2026 in 107 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://opendata.cat/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.xaviviro. Endpoint host: opendata.cat. ARD identifier: urn:air:io.github.xaviviro:mcp:opendata-cat.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.