gov.br APIs MCP

io.github.thalisantunesPublished by GitHub account thalisantunesv0.2.0Updated Oct 26, 2026

A catalog-driven gateway over Brazilian government APIs, loading OpenAPI specs on demand.

VerifiedSTDIODesktop onlyDeveloper ToolsData & Analytics

Overview

AI-generated overview

Catalog-driven gateway that lets an assistant search, describe and call Brazilian government APIs (IBGE, Banco Central, Câmara, Serpro and more) from one…

What you can do
  • Search and list the bundled catalog of 116 Brazilian government APIs by keyword, category or status
  • Describe an API entry and, where an OpenAPI spec exists, list its operations and parameter, request and response schemas
  • Call any catalogued endpoint with a chosen method, query, body and headers, with base URL and auth resolved from the catalog
  • Check which environment variables each API needs and whether it is callable right now
  • Extend or override the catalog with local YAML files and extra allowlisted hosts
When to use it
Useful when you work with Brazilian public data or services and want an assistant to look up and query them without wiring one tool per endpoint. It fits research on transparency, legislative, statistical or financial data, and Serpro or meia-entrada flows once the matching credentials or contracts exist.
Requirements
Runs locally over stdio, typically via uvx from PyPI or a container. Most public-tier APIs need no key; others need environment variables such as TRANSPARENCIA_API_KEY, DATAJUD_API_KEY, DADOSGOV_API_KEY, MEIAENTRADA_CODIGO_ACESSO or the SERPRO_* OAuth2 client id and secret pairs. Variables must be set in the MCP client's env block, since .env files are not read. Network access to allowlisted gov.br, leg.br and jus.br hosts.
Before you install
The catalog decides where your credentials are sent, so only add hosts via GOVBR_EXTRA_ALLOWED_HOSTS if you trust them, and treat GOVBR_CATALOG_DIR as trusted input. Serpro APIs are paid per call under a commercial contract. call_api can send POST, PUT, PATCH and DELETE requests, so it can change remote data. Entries flagged pii return personal data such as CPF, name and photo into the transcript, and the CIE validators are callable without any credential.

Installation

In SourceWeft

  1. Open gov.br APIs MCP in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

govbr-apis-mcp

[CI]

MCP server that turns Brazilian government APIs into Claude-callable tools through a catalog-driven gateway: instead of one tool per endpoint (hundreds — would blow up client context), five generic tools operate over a local YAML catalog of 116 APIs.

Only the entries that declare an openapi_url have a spec to load: today the Câmara dos Deputados and the Portal da Transparência, 2 of the 116. For those, describe_api loads the OpenAPI spec on demand. Every other callable entry (see the "Callable today?" column below) is reached through call_api alone, using the endpoints in its description and docs_url.

Catalog tiers

TierFileAccess modelCallable today?
publicsrc/govbr_apis_mcp/catalog_data/public.yamlFree — no auth or free API key (IBGE, Banco Central, Câmara, Senado, Portal da Transparência, DataJud, Ipeadata, dados.gov.br…)Yes
serprosrc/govbr_apis_mcp/catalog_data/serpro.yamlSerpro commercial (loja.serpro.gov.br) — OAuth2 client credentials per contracted API, paid per callWith a Serpro contract: set the SERPRO_* variables
meia-entradasrc/govbr_apis_mcp/catalog_data/meia_entrada.yamlEligibility sources for half-price tickets (student CIE, ID Jovem, PcD, e-MEC) — see docs/meia-entrada.md and the POCCIE yes (DNE and FESN); the rest is manual
conectasrc/govbr_apis_mcp/catalog_data/conecta.yamlConecta gov.br — restricted to public-sector entities; 95 APIs indexed as stubs for discoveryNot yet (adhesion pending)

The Conecta tier exists so the catalog reflects the whole landscape now, and becomes callable later by filling in base_url + credentials — the OAuth2 client-credentials flow is already implemented (Serpro uses the same one).

Tools

  • search_catalog(query, category?) — accent-insensitive keyword search; reports total matches and whether the list was truncated.
  • list_apis(category?, status?, limit?) — enumerate entries, callable ones first (by the catalog's status, not by whether your credentials are set; filter it: ~95 Conecta stubs otherwise dominate the output).
  • describe_api(api_id, path?, method?) — catalog metadata + OpenAPI operation list; with path, parameter/request/response schemas ($refs inlined, depth-limited). Reads OpenAPI 3 and Swagger 2.0, as JSON or YAML.
  • call_api(api_id, path, method?, query?, body?, headers?) — invoke an endpoint; base URL and auth resolved from the catalog entry.
    • method is GET, HEAD, POST, PUT, PATCH, DELETE or OPTIONS; anything else returns an error with allowed_methods. A body is accepted only with POST, PUT and PATCH.
    • path is relative to the base_url. . and .. segments (after up to three rounds of percent-decoding, with \ read as / and ; parameters removed) and any path that leaves the base_url prefix are rejected. So is a # (a fragment is never sent; write a literal one as %23) or a control character.
    • A query string embedded in path is merged with query; a key in query replaces the embedded one, and a list value repeats the key.
    • Caller headers are matched case-insensitively, with _ equal to -. Authorization, Proxy-Authorization, Host, Cookie and Accept-Encoding, plus connection, proxy, forwarding and method-override headers, are dropped and reported in ignored_headers (the full list is in server.py). The managed credential is applied last and always wins. A header with an invalid name or value is not ignored: it fails the call with an error.
    • Method, body, headers and path are validated before any OAuth2 token is requested, and invalid input comes back as {"error": ...}.
    • A 3xx is not followed: the response carries its location (redacted, resolved against the requested URL). Response bodies are cut at 60,000 characters.
  • credentials_status(api_id?) — which env vars each API needs and whether they're set, plus callable: whether call_api would accept the entry right now (available and unstable entries; requires_contract ones only once their env vars are set).

POC: meia-entrada de estudante

Fluxo funcional ponta a ponta (código da CIE → decisão de elegibilidade), incluindo modo demo sem credencial: poc/README.md.

Install

bash
python3 -m venv .venv.venv/bin/pip install -e '.[dev]'.venv/bin/pytest

Register in Claude Code (.mcp.json or claude mcp add):

json
{  "mcpServers": {    "govbr-apis": {      "command": "/path/to/govbr-apis-mcp/.venv/bin/govbr-apis-mcp",      "env": {        "TRANSPARENCIA_API_KEY": "...",        "DATAJUD_API_KEY": "..."      }    }  }}

From PyPI: uvx govbr-apis-mcp (set "command": "uvx" and "args": ["govbr-apis-mcp"] in the entry above; no checkout needed). Each release is published to PyPI and to the MCP Registry automatically (publish.yml).

Or run it in a container. The server speaks stdio, so keep -i:

bash
docker build -t govbr-apis-mcp . && docker run -i --rm -e TRANSPARENCIA_API_KEY=... govbr-apis-mcp

Credentials

All secrets come from env vars declared per entry in the catalog (auth_config). Nothing is stored in the repo. .env.example lists the variables. Entries with a free key carry a signup_url; Serpro credentials come with the contract, at loja.serpro.gov.br. credentials_status reports readiness.

The server does not read .env files, and MCP clients start it with a minimal environment, so an export in your shell may never reach it. Put the variables in the client's env block (the example above, or claude mcp add -e KEY=value). For a container, copy .env.example to a git-ignored file such as .env.local, fill in the copy and pass it with docker run --env-file .env.local. Never put real values in .env.example: it is versioned.

API keys (the value together with any prefix) are stripped of surrounding whitespace and must be printable ASCII; otherwise the call fails with credential in <VAR> contains invalid characters, without echoing the value. OAuth2 client ids and secrets are only stripped: they travel base64-encoded, so any text works. The access token the endpoint returns must be printable ASCII too. When the token endpoint fails, the call returns an error and the token_url, with neither the response body nor any secret.

Auth profiles: none, api_key (static header, optional value prefix — e.g. DataJud's APIKey <key>), oauth2_client_credentials (token endpoint + id/secret, in-memory token cache; used by Serpro today, by Conecta after adhesion).

Extending the catalog

Add an entry to a YAML file in src/govbr_apis_mcp/catalog_data/. The directory is package data, so the wheel, uvx and the Docker image all carry the catalog. Minimum fields: id, name, provider, category, status, auth. Add openapi_url when the API publishes a spec — describe_api then works with zero code. Regenerate the Conecta tier with .venv/bin/python scripts/scrape_conecta.py. It leaves the file alone when the page yields no APIs, an id the catalog would reject, or fewer than half the current entries (--force overrides only the last check).

Entries are validated on load: ids must be filename-safe, URLs must be https on an allowlisted host (*.gov.br, *.leg.br, *.jus.br plus a few named hosts), and a hostname may only contain [a-z0-9.-] (write internationalized names in punycode). This is a security boundary, not style — the catalog decides where your credentials are sent. Add a host with GOVBR_EXTRA_ALLOWED_HOSTS only if you trust it with them; the same hostname rule applies to it.

To override entries without forking (e.g. filling in Conecta base URLs after adhesion), point GOVBR_EXTRA_CATALOG_DIR at a directory of .yaml or .yml files whose same-id entries win. A directory that does not exist or holds no entries is an error, and so is an id repeated inside it; an empty value counts as unset. GOVBR_CATALOG_DIR replaces the base catalog entirely and should be treated as trusted input.

Development

bash
python3 -m venv .venv.venv/bin/pip install -e '.[dev]'.venv/bin/ruff check ..venv/bin/ruff format --check ..venv/bin/pytest

CI runs ruff on Python 3.12 and the test suite on 3.11–3.14, then builds the wheel and loads the catalog from a clean install.

Security notes

  • Responses are never written to disk. Only OpenAPI specs are cached, in $XDG_CACHE_HOME/govbr-apis-mcp/ (or ~/.cache/govbr-apis-mcp/) for 24 hours, under a file name derived from sha256(api_id + "\n" + openapi_url): never the id itself, and a changed openapi_url never serves the old spec. OAuth2 tokens live in memory only.
  • call_api does not follow redirects — credentialed requests cannot be steered to another host by a 3xx; the response carries the (redacted) location instead. It always sends Accept-Encoding: identity, so a server has no reason to compress. The 60,000-character cut counts decoded text, though: a server that compresses anyway can still inflate a small chunk before the cut (an accepted risk; see the roadmap).
  • Cookies an API sets are never stored or sent back, so one API cannot plant a cookie that another would receive.
  • Spec fetches follow redirects only by hand: at most 5 hops, and every URL (the first and each Location) must be https on an allowlisted host before it is requested. The body is capped at 5 MiB, JSON and YAML are accepted (YAML with aliases, including merge keys that rely on them, is refused), and the document must carry openapi or swagger. A compressed response is refused and the whole download has a 60-second deadline; both come back as spec_error.
  • The httpx and httpcore loggers stay at WARNING, so httpx logs no request URL (query string included).
  • Entries flagged pii: true return personal data (CPF, name, photo) into the client transcript. Today: meiaentrada-cie-validador, fesn-cie-validador (callable without any credential: whoever holds a use code gets the holder's data) and the three Serpro entries.

Roadmap

  • Conecta adhesion as a public-sector entity → fill gateway base URLs + credentials
  • Per-API OpenAPI URLs for Conecta entries (linked from each detail page)
  • Serpro trial-mode toggle (call -trial base URLs with the published demo token)
  • Per-call cost guard for paid Serpro APIs
  • Bounded decompression for compressed upstream responses
  • Pleito à SNJ para a API conecta-id-jovem (admite instituição privada)
  • Fallback documental para CIE fora da base DNE (DCEs e entidades estaduais)

License

MIT - see LICENSE.

Source: README.md at commit c4957f2

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.0LatestOct 19, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts