uruguay-mcp
The uruguay-mcp server provides AI agents with structured access to Uruguay's open government data through 5 meta-tools, 84 data tools across 17 modules, 54 prompts, and 36 resources.
Core Meta-Tools
discover_tools(query, module?, limit?)— Search for relevant data tools using natural language; returns ranked tools with argument schemascall_tool(name, arguments)— Invoke any data tool by name with validated argumentslist_modules()— Browse all 17 available data-source modules and their tool countsplan_query(goal)— Get a multi-step plan with candidate tools for complex, broad goalsexecute_batch(calls)— Run multiple tool calls concurrently with per-call error isolation
Data Sources Available
🏛️ National Data Catalog — ~2,680 datasets from 72 organizations via CKAN
💵 Central Bank (BCU) — Exchange rates and currency data
📊 Statistics Institute (INE) — National statistics and DataStore queries
🚌 Montevideo City — City datasets and real-time public transport
🛒 Public Procurement (ACCE) — Government contracts and tenders
⚖️ Legislation (IMPO) — Laws, regulations, and the Diario Oficial
🧾 Tax Authority (DGI) — Reference values (UI, IPC, ITP) and tax rates
🌦️ Weather (INUMET) — Station data, forecasts, and alerts
🏛️ Parliament — Legislative datasets and activity
🗺️ Spatial Data (IDE) — WFS layers, cadastral parcels, and geocoding
🎓 Education (ANEP) — School directories and education datasets
🏥 Health (MSP/FNR) — Clinics, health datasets, and medication spending
🤝 Social Programs (MIDES) — Social programs and resource directory
🧓 Social Security (BPS) — Pensions, benefits, and contributor statistics
📰 Government News — Latest releases and full-text news search
🌐 gub.uy Service Catalog — Public service catalog
🗄️ Local DataStore — Load CSV/CKAN data and run cross-source SQL JOINs
Additional Capabilities
Access 54 reusable prompts (parameterized Spanish instruction templates) and 36 static reference resources
Configurable via environment variables (language, caching, rate limiting, module filtering)
Easy integration with Claude Desktop via
uvxor pip install
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., "@uruguay-mcp search for datasets about education in Uruguay"
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.
🇺🇾 uruguay-mcp
Structured AI-agent access to Uruguay's open government data Acceso estructurado de agentes de IA a los datos abiertos del Estado uruguayo
🌎 Español · English
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 |
| Rank data tools relevant to a natural-language need (returns their argument schemas) |
| Invoke a data tool by name (validates arguments) |
| List data-source modules and their tool counts |
| Surface candidate tools for a multi-step goal |
| 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.
Related MCP server: PNDA-MCP
📚 Data sources (modules)
Module | Source | Protocol | Tools | |
🏛️ |
| catalogodatos.gub.uy — national CKAN catalog (~2680 datasets, 72 orgs) + DataStore SQL | CKAN REST | 9 |
💵 |
| Banco Central del Uruguay — exchange rates | SOAP ( | 4 |
📊 |
| Instituto Nacional de Estadística — ANDA studies + national CKAN DataStore queries | REST | 7 |
🌐 |
| gub.uy public API / service catalog | CKAN REST | 4 |
🚌 |
| Intendencia de Montevideo — city CKAN + realtime transport | CKAN + REST | 11 |
🗄️ |
| Cross-source SQLite workspace — load CSV/CKAN data, run read-only SQL JOINs | local SQLite | 4 |
🛒 |
| Agencia de Compras y Contrataciones del Estado — public procurement (OCDS) | OCDS REST/RSS + CKAN | 4 |
⚖️ |
| IMPO — legislation, normativa & Diario Oficial | REST (JSON) | 6 |
🧾 |
| DGI (tax authority) — reference values (UI, IPC, ITP & late-payment rates) as | scrape + ODS/PDF | 4 |
🌦️ |
| Instituto Uruguayo de Meteorología — stations, forecast & alerts | REST + HTML | 3 |
🏛️ |
| Parlamento del Uruguay — datasets, attendance & activity (CKAN-backed) | CKAN REST | 4 |
🗺️ |
| IDE Uruguay (AGESIC) — spatial data: WFS layers, cadastral parcels & geocoding | WFS 2.0 + REST | 5 |
🎓 |
| ANEP / education — datasets & school directories (national CKAN, org=anep) | CKAN REST | 3 |
🏥 |
| Salud (MSP / FNR) — health datasets, clinics & medication spending | CKAN REST | 5 |
🤝 |
| MIDES — social programs & the Guía de Recursos service directory | CKAN + HTML | 4 |
🧓 |
| Banco de Previsión Social — "BPS en Cifras" observatory: pensions, benefits & contributors (live indicators) | REST (JSON) | 5 |
📰 |
| 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-mcpOne-command install into Claude
uruguay-mcp installMerges 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 |
|
| Language for human-facing strings ( |
|
| HTTP timeout (seconds) |
|
| Response cache TTL (seconds) |
|
| Max requests/sec per host |
| (all) | Comma-separated module allowlist |
| (unset) | OAuth2 client id for the Montevideo transport API |
| (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
Available Tools
5 toolscall_toolC
Invoke a data tool by name with the given arguments.
Inputs: name (required), arguments.
discover_toolsB
Find data tools relevant to a natural-language need.
Returns ranked tools with their argument schemas. Use this first, then
invoke the chosen tool via call_tool.
Inputs: query (required), module, limit. Returns: object
execute_batchA
Run several tool calls concurrently with per-call error isolation.
calls is a list of {"name": ..., "arguments": {...}}. A failure in
one call does not abort the others.
Inputs: calls (required). Returns: object
list_modulesA
List the available data-source modules and how many tools each offers.
Inputs: no named parameters. Returns: object
plan_queryA
Sketch a plan: surface candidate tools across modules for a broad goal.
For multi-step needs, this returns the most relevant tools so the model can chain them (e.g. search a dataset, then query its datastore).
Inputs: goal (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose: call_tool for invocation, discover_tools for natural language search, execute_batch for concurrent calls, list_modules for module overview, and plan_query for multi-step planning. No overlap in functionality.
All tool names follow a consistent verb_noun pattern in snake_case (call_tool, discover_tools, execute_batch, list_modules, plan_query). The naming is predictable and uniform.
With 5 tools, the server is well-scoped for a meta-tool that discovers and invokes other data tools. The number feels complete without being excessive.
The tool surface covers the full workflow: discovering tools (discover_tools), planning multi-step queries (plan_query), invoking individual tools (call_tool), batch execution (execute_batch), and listing available modules (list_modules). No obvious gaps for its stated purpose.
Maintenance
Related MCP Connectors
Discover, resolve, and query official Brazilian economic data with semantic search and provenance.
Argentina's official public data (INDEC, BCRA, 38 portals): search, read tables, cited answers.
Official statistics for AI agents: Eurostat, World Bank, OECD, IMF and WHO data for 150+ countries.
Brazilian public data API for AI agents. BCB, IBGE, CVM, B3, compliance. x402 payments on Base.
Related MCP Servers
- AlicenseAqualityAmaintenanceEnables AI assistants to search, explore, and query any CKAN open data portal through natural language, making public datasets accessible without requiring knowledge of the portal's API.202,377 npm61MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to search and retrieve metadata and data files from Peru's National Open Data Platform, and generate Jupyter notebooks for data analysis.5Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables querying Brussels Open Data datasets through natural language or direct tool calls, including search, metadata retrieval, and SQL-like queries.123 npmMIT
- AlicenseBqualityAmaintenanceEnables AI agents and developers to search and inspect Spanish public data sources, learn their endpoints and pitfalls, and retrieve ready-made data such as municipal profiles, economic indicators, company records, procurement, subsidies, and location reports.13130Creative Commons Zero v1.0 Universal