CuritibAI
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@CuritibAI find open datasets about public health in Curitiba"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
CuritibAI
A read-only MCP server that lets AI assistants search the catalogue of the Portal de Dados Abertos de Curitiba (Brazil) and list each dataset's files.
Unofficial. Not affiliated with, endorsed by or connected to the Prefeitura de Curitiba. Data comes from the portal as it is; always confirm important information at the source.
Tools
Both tools are read-only. A successful call returns {data, source_url, fetched_at, license_note}.
When the portal fails, times out or changes format, the tool returns {"error":"source_unavailable"} as JSON text with
isError: true, and no data.
Tool | Input | Returns | Source (checked 2026-11-19) |
|
| Dataset id, title, publisher, description, formats, last update, detail URL; | Portal search form ( |
|
| The dataset's files: name, format, size, last update, link and data-dictionary link (50 per page). Links only: the files are not downloaded | Portal detail page + |
The file links point to mid-dadosabertos.curitiba.pr.gov.br. That host's robots.txt says Disallow: /, so this
server never opens them; a person can open them in a browser.
Details for each source (format, terms, robots.txt) are in docs/sources.md.
Related MCP server: Base dos Dados MCP
Deferred
Tool | Reason |
| File hosts disallow automated access (robots.txt) and the 156 CSV is 137 MB; needs permission or an official API |
| Same reason |
| Same reason |
Bus lines, timetables and stops | The URBS website is out of scope (it refuses non-browser clients) and its WebService needs a login. See "Alternatives" |
| Their files are only on the hosts whose robots.txt disallows automated access |
| No source found |
Alternatives (not recommended, not tested)
gtfs-mcp (MIT) is a generic GTFS MCP server, and urbs-gtfs (Apache-2.0 pipeline code) publishes a third-party GTFS feed for Curitiba. Two facts, checked 2026-11-19:
urbs-gtfs builds its feed from C3SL/UFPR data "subject to their terms"; that host's robots.txt disallows automated access.
The latest feed (published 2026-10-27) expired on 2026-11-02 (
feed_end_dateinfeed_info.txt).
gtfs-mcp was not run here.
Out of scope by design: gov.br/CPF login, payments, scheduling, opening or looking up 156 tickets, personal data, any tool that writes, and real-time feeds that need a key.
Run it
Requires Node.js 22.12 or newer.
git clone https://github.com/Bossmann007/curitibai.git
cd curitibai
npm ci
npm run build
node dist/server.js # speaks MCP over stdio; it prints nothing elseMCP client configuration (for example Claude Desktop's claude_desktop_config.json):
{
"mcpServers": {
"curitibai": {
"command": "node",
"args": ["/absolute/path/to/curitibai/dist/server.js"]
}
}
}Claude Code: claude mcp add curitibai -- node /absolute/path/to/curitibai/dist/server.js
Privacy and safety
No telemetry, no secrets, no
.env, no files written. The cache is in memory only (10 minutes) and is keyed by the request sent to the portal.The server contacts exactly one host,
https://dadosabertos.curitiba.pr.gov.br, on the default port and without credentials. Every redirect hop is checked against it, and inputs are a search term and a dataset GUID, never a URL.Requests use a generic User-Agent,
curitibai-mcp/0.1, a 10 s timeout per request and an 8 MB response cap.Text from the portal is returned as plain data fields with HTML removed. It is never meant as instructions.
Limits
The portal is a website, not a documented API. If its HTML or JSON changes, the tools return
source_unavailable.The search matches accents literally ("saude" and "saúde" can differ) and finds nothing for some everyday words ("onibus", "feira"). Later result pages can be slow; when one times out, the tool returns what it has with
partial: true.dataset_filesdoes not check that the links work, and it cannot show the contents of a file.Licence: portal data is CC BY 4.0. The portal's usage rules require citing the source and a disclaimer, and each result's
license_notecarries both.
Development
scripts/verify # npm ci, tsc --noEmit, eslint, vitest, build, stdio smoke test; npm audit reported separatelyTests run offline: every network call is stubbed, and an unstubbed call fails the test. Parser tests use trimmed real
responses in test/fixtures/.
License
Code: Apache-2.0. The data belongs to its publishers under their own terms (see above).
Available Tools
2 toolsdataset_filesList a Curitiba open dataset's filesARead-onlyIdempotent
List the downloadable files of one Portal de Dados Abertos de Curitiba dataset: name, format, size, last update, link and data-dictionary link. Returns the links without fetching them. Read-only.
Inputs: dataset_id (required), page. Returns: data, fetched_at, source_url, license_note
open_datasets_searchSearch Curitiba open datasetsARead-onlyIdempotent
Search the Portal de Dados Abertos de Curitiba catalogue. Returns dataset ids, titles, publishers and detail-page URLs; pass an id to dataset_files. Read-only (the portal search is a form POST).
Inputs: query (required), limit. Returns: data, fetched_at, source_url, license_note
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct roles: one searches the catalogue and the other lists files for a specific dataset id. There is no realistic overlap or risk of misselection.
Both names use snake_case, but their patterns differ: dataset_files is a noun phrase while open_datasets_search embeds a verb at the end. The naming is readable but does not establish a predictable verb_noun convention.
Two tools is thin for an open-data portal, though each has a clear purpose. The surface feels minimal rather than comfortably scoped.
Search and file listing cover the core discovery workflow, but there is no tool for fetching/downloading files or retrieving richer dataset metadata beyond the search result fields. Agents can follow returned links externally, but the server itself has notable gaps.
Maintenance
Related MCP Connectors
Read-only MCP server exposing a user ORANO library to their own AI agent.
MCP server for Brazilian Federal Senate open data (legislative, administrative, e-Cidadania).
This MCP server provides seamless access to Malaysia's government open data, including datasets, w…
Search and preview datasets publicly. Account-required full data via MCP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn MCP server that provides tools for intelligently querying, analyzing, and retrieving datasets from Toronto's CKAN-powered open data portal. It enables AI assistants to perform natural language searches, inspect data structures, and track dataset update frequencies across the city's open data catalog.12-
- AlicenseNot gradedqualityDmaintenanceThis MCP server provides AI-optimized access to Brazil's largest open data platform, Base dos Dados, enabling dataset search and direct BigQuery SQL execution for Brazilian public datasets.1MIT
- FlicenseAqualityDmaintenanceA read-only MCP server that enables AI assistants to search files, list directories, retrieve system info, and get file metadata on the local file system.4-
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to discover and inspect research datasets via a read-only MCP server, offering search, variable listing, and metadata retrieval without reading data files.-