uruguay-mcp
Enables AI agents to query Uruguay's open government data from multiple sources (national catalog, Central Bank, statistics institute, Montevideo city data and transport, and gub.uy service catalog) through a meta-discovery layer.
README
<div align="center">
<img src="https://flagcdn.com/w160/uy.png" alt="Bandera de Uruguay" width="120" />
🇺🇾 uruguay-mcp
Structured AI-agent access to Uruguay's open government data <br> Acceso estructurado de agentes de IA a los datos abiertos del Estado uruguayo
🌎 Español · English
</div>
An MCP server that gives AI agents structured access to Uruguay's open government data — the national data catalog, the Central Bank, the statistics institute, Montevideo's city data & realtime transport, spatial data (IDE), education, health, social programs, government social-security statistics (BPS), tax reference values (DGI), news, and the gub.uy service catalog — behind a single meta-discovery layer.
✨ Why a meta-discovery layer?
Instead of flooding the model with hundreds of tool definitions, the server exposes five meta-tools. The model searches for what it needs, then invokes the matching data tool by name. The prompt-visible surface stays constant no matter how many data sources are added.
| Meta-tool | Purpose |
|---|---|
discover_tools(query, module?, limit?) |
Rank data tools relevant to a natural-language need (returns their argument schemas) |
call_tool(name, arguments) |
Invoke a data tool by name (validates arguments) |
list_modules() |
List data-source modules and their tool counts |
plan_query(goal) |
Surface candidate tools for a multi-step goal |
execute_batch(calls) |
Run several calls concurrently with per-call error isolation |
Every tool returns a unified envelope: { "_meta": { source, cached, lang, timestamp }, "data": ... }.
At a glance: 5 meta-tools + 84 data tools across 17 modules, plus 54 prompts and 36 resources.
📚 Data sources (modules)
| Module | Source | Protocol | Tools | |
|---|---|---|---|---|
| 🏛️ | catalogodatos |
catalogodatos.gub.uy — national CKAN catalog (~2680 datasets, 72 orgs) + DataStore SQL | CKAN REST | 9 |
| 💵 | bcu |
Banco Central del Uruguay — exchange rates | SOAP (zeep) |
4 |
| 📊 | ine |
Instituto Nacional de Estadística — ANDA studies + national CKAN DataStore queries | REST | 7 |
| 🌐 | gubuy |
gub.uy public API / service catalog | CKAN REST | 4 |
| 🚌 | montevideo |
Intendencia de Montevideo — city CKAN + realtime transport | CKAN + REST | 11 |
| 🗄️ | datastore |
Cross-source SQLite workspace — load CSV/CKAN data, run read-only SQL JOINs | local SQLite | 4 |
| 🛒 | acce |
Agencia de Compras y Contrataciones del Estado — public procurement (OCDS) | OCDS REST/RSS + CKAN | 4 |
| ⚖️ | impo |
IMPO — legislation, normativa & Diario Oficial | REST (JSON) | 6 |
| 🧾 | dgi |
DGI (tax authority) — reference values (UI, IPC, ITP & late-payment rates) as .ods + statistical bulletins |
scrape + ODS/PDF | 4 |
| 🌦️ | inumet |
Instituto Uruguayo de Meteorología — stations, forecast & alerts | REST + HTML | 3 |
| 🏛️ | parlamento |
Parlamento del Uruguay — datasets, attendance & activity (CKAN-backed) | CKAN REST | 4 |
| 🗺️ | ide |
IDE Uruguay (AGESIC) — spatial data: WFS layers, cadastral parcels & geocoding | WFS 2.0 + REST | 5 |
| 🎓 | educacion |
ANEP / education — datasets & school directories (national CKAN, org=anep) | CKAN REST | 3 |
| 🏥 | salud |
Salud (MSP / FNR) — health datasets, clinics & medication spending | CKAN REST | 5 |
| 🤝 | mides |
MIDES — social programs & the Guía de Recursos service directory | CKAN + HTML | 4 |
| 🧓 | bps |
Banco de Previsión Social — "BPS en Cifras" observatory: pensions, benefits & contributors (live indicators) | REST (JSON) | 5 |
| 📰 | noticias |
gub.uy government news — latest releases & full-text search | HTML scrape | 2 |
The transport surface of montevideo needs OAuth2 credentials
(URUGUAY_MCP_MVD_CLIENT_ID / URUGUAY_MCP_MVD_CLIENT_SECRET); without them the
transport tools return a typed validation_error while the CKAN tools work
unauthenticated.
🧩 Prompts & Resources
Each module also registers reusable prompts (parameterized Spanish
instruction templates) and resources (static reference docs under the
uru://<module>/<path> URI scheme), exposed natively through FastMCP.
- 54 prompts — e.g.
bcu_cotizacion_dolar_hoy,catalogo_buscar_por_tema,bps_pasividades_actuales,dgi_valor_referencia,ine_buscar_estudios,montevideo_proximo_bus,datastore_unir_dos_fuentes,acce_analizar_compra,impo_consultar_norma,inumet_clima_actual,ide_consultar_catastro,salud_consultar_medicamentos,noticias_ultimas. - 36 resources — e.g.
uru://bcu/codigos-moneda,uru://bps/catalogo-indicadores,uru://dgi/catalogo-valores,uru://catalogodatos/guia-de-uso,uru://montevideo/credenciales-transporte,uru://acce/glosario-ocds,uru://impo/esquema,uru://inumet/variables,uru://ide/capas-destacadas,uru://salud/fuentes,uru://mides/guia-recursos.
See EXAMPLES.md for end-to-end usage scenarios, including
cross-source ones via plan_query / execute_batch and SQL JOINs through the
datastore module.
🚀 Quick start
# Run directly from PyPI (once published)
uvx uruguay-mcp
# …or install it
pip install uruguay-mcp # or: uv pip install uruguay-mcp
uruguay-mcp
One-command install into Claude
uruguay-mcp install
Merges the server into Claude Desktop's config (preserving existing
mcpServers and unrelated keys) and prints a ready-to-paste snippet for Claude
Code / Cursor. Restart the client afterwards.
Claude Desktop config (manual)
{
"mcpServers": {
"uruguay-mcp": { "command": "uruguay-mcp" }
}
}
Run options
uruguay-mcp # stdio (default)
uruguay-mcp --transport sse --port 8000
uruguay-mcp --modules catalogodatos,bcu # load only some modules
uruguay-mcp --verbose # INFO logs (--debug for DEBUG)
⚙️ Configuration
All via URUGUAY_MCP_* environment variables:
| Variable | Default | Meaning |
|---|---|---|
URUGUAY_MCP_LANG |
es |
Language for human-facing strings (es/en) |
URUGUAY_MCP_HTTP_TIMEOUT |
30 |
HTTP timeout (seconds) |
URUGUAY_MCP_CACHE_TTL |
900 |
Response cache TTL (seconds) |
URUGUAY_MCP_RATE_LIMIT_RPS |
5 |
Max requests/sec per host |
URUGUAY_MCP_MODULES |
(all) | Comma-separated module allowlist |
URUGUAY_MCP_MVD_CLIENT_ID |
(unset) | OAuth2 client id for the Montevideo transport API |
URUGUAY_MCP_MVD_CLIENT_SECRET |
(unset) | OAuth2 client secret for the Montevideo transport API |
🏗️ Architecture
src/uruguay_mcp/
├── server.py # FastMCP wiring; meta-tools + registered prompts + resources
├── cli.py # `uruguay-mcp` / `uruguay-mcp install`; -v/--debug logging
├── meta/ # discovery layer
│ ├── tools.py # the 5 meta-tools
│ └── search.py # BM25-lite ranking over the registry
├── shared/ # reused by every module
│ ├── config.py # env-driven settings (URUGUAY_MCP_*)
│ ├── http.py # async client: retries (tenacity) + per-host rate limit
│ ├── cache.py # async TTL cache
│ ├── envelope.py # unified {_meta, data} response (+ UTC timestamp)
│ ├── i18n.py # es/en messages
│ ├── errors.py # typed, localized errors
│ └── registry.py # tool/prompt/resource registry; @tool/@prompt/@resource
└── modules/ # one self-contained package per data source
├── catalogodatos/ ├── bcu/ ├── ine/
├── gubuy/ ├── montevideo/ ├── datastore/
├── acce/ ├── impo/ ├── inumet/
├── parlamento/ ├── ide/ ├── educacion/
├── salud/ ├── mides/ ├── noticias/
├── bps/ └── dgi/
Each module package is independent (constants · schemas · client ·
tools · optional prompts/resources). Importing the package self-registers
everything it offers.
🛠️ Development
uv venv && uv pip install -e ".[dev]"
uv run pytest # 252 unit tests (HTTP mocked, offline) · 86% coverage
uv run pytest -m integration # hits live government APIs
uv run ruff check src tests
uv run pyright
🙌 Acknowledgements
Built on data published by AGESIC, BCU, INE and the Intendencia de Montevideo under Uruguay's open-data law (Nº 18.381). This project is an independent client and is not affiliated with those institutions.
📄 License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。