# OpenArg — Argentina public data (remote · mcp.openarg.org)

Argentina's official public data (INDEC, BCRA, 38 portals): search, read tables, cited answers.

- Trust score: 81/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `mcp.openarg.org`: 81/100 (this document), [markdown](https://verifymcp.io/servers/org-openarg-datos-publicos/mcp.md), [page](https://verifymcp.io/servers/org-openarg-datos-publicos/mcp)

## Channel facts

- Endpoint: `https://mcp.openarg.org/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1997 tokens (~332/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - Manipulation not yet verified: only 2 of 7 captured unit(s) of tool text has been judged so far, so we will not certify text no model has read as clean.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the OpenArg — Argentina public data MCP server?

OpenArg — Argentina public data is a hosted endpoint at https://mcp.openarg.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http org-openarg-datos-publicos 'https://mcp.openarg.org/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "org-openarg-datos-publicos": {
      "url": "https://mcp.openarg.org/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "org-openarg-datos-publicos": {
      "type": "http",
      "url": "https://mcp.openarg.org/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.org-openarg-datos-publicos]
url = "https://mcp.openarg.org/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "org-openarg-datos-publicos": {
      "type": "remote",
      "url": "https://mcp.openarg.org/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add org-openarg-datos-publicos --url 'https://mcp.openarg.org/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  org-openarg-datos-publicos:
    url: "https://mcp.openarg.org/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "org-openarg-datos-publicos": {
      "Transport": "http",
      "Url": "https://mcp.openarg.org/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add org-openarg-datos-publicos -t streamable-http -u 'https://mcp.openarg.org/mcp'
```

### Other

```json
{
  "mcpServers": {
    "org-openarg-datos-publicos": {
      "type": "http",
      "url": "https://mcp.openarg.org/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-30 (score 81, 0)

- [security] Stability: 0.97 → pass

### 2026-10-29 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (6)

### `consultar_datos_publicos` (~190 tokens)

Consultar datos públicos de Argentina

Responde una pregunta sobre datos públicos oficiales de Argentina, con fuentes.

Ejemplos: "¿Cuál fue la tasa de desempleo del último trimestre?",
"Evolución del IPC en 2025", "¿Cuántos diputados tiene cada bloque?",
"Presupuesto ejecutado por el Ministerio de Salud en 2024".
La respuesta incluye los datasets usados (con link al portal oficial),
advertencias sobre la calidad o cobertura del dato, y cuántas preguntas
le quedan este mes al usuario. Cada respuesta descuenta 1 de sus preguntas
del mes (10 gratis); un error, un corte por tiempo o la misma pregunta
repetida dentro de los 5 minutos no descuentan. Si podés responder con
\`buscar_datasets` + `obtener_datos` o `agregar_datos`, preferí esas.

Input parameters:

- `pregunta` (string, required)

Output parameters:

- `result` (string)

### `listar_fuentes` (~43 tokens)

Listar fuentes de datos de OpenArg

Lista los portales de datos abiertos que cubre OpenArg y cuántos datasets tiene cada uno.

No descuenta preguntas: cuenta como un pedido del modo datos.

Output parameters:

- `result` (string)

### `buscar_datasets` (~149 tokens)

Buscar datasets públicos de Argentina

Busca en el catálogo de OpenArg (más de 30.000 datasets de portales oficiales).

Devuelve título, portal, descripción, link a la fuente oficial y las tablas
consultables de cada dataset (usalas con `describir_tabla` y `obtener_datos`).
\`texto` es lo que buscás, en castellano ("tasas de interés BCRA", "matrícula
escolar CABA"). `portal` filtra por portal (ver `listar_fuentes`).
\`limite` entre 1 y 25. No descuenta preguntas.

Input parameters:

- `limite` (integer)
- `portal`
- `texto` (string, required)

Output parameters:

- `result` (string)

### `describir_tabla` (~173 tokens)

Describir una tabla de OpenArg

Muestra las columnas (con su tipo), cantidad de filas, período cubierto, frescura y una muestra de una tabla.

\`tabla` es el nombre que devuelve `buscar_datasets`. Usalo antes de
\`obtener_datos` o `agregar_datos` para saber qué columnas pedir y qué
fechas existen. La frescura dice cuándo leyó OpenArg la tabla de su fuente,
cuál es el último dato y, sólo si la tabla es una foto del período en curso,
su fecha de corte. La fecha de lectura no es la de los datos: una tabla de
un período pasado o sin columna de fecha no es vigente por haberse leído
hoy. No presentes como actual un dato viejo. No descuenta preguntas.

Input parameters:

- `tabla` (string, required)

Output parameters:

- `result` (string)

### `obtener_datos` (~457 tokens)

Obtener datos de una tabla de OpenArg

Trae filas de una tabla, en CSV, con la fuente oficial.

Para un total, promedio, conteo, mínimo, máximo o ranking NO traigas filas para
sumarlas: usá `agregar_datos`.
\- `columnas`: las que quieras (por defecto, todas); nombres exactos de `describir_tabla`.
\- `desde` / `hasta`: período, como AAAA, AAAA-MM o AAAA-MM-DD, sobre la columna de
  fecha (o de año).
\- `filtros`: hasta 5. Igualdad: {"provincia": "Córdoba"}. Con operador, una lista:
  [{"columna": "monto", "operador": "mayor_que", "valor": "1000000"},
  {"columna": "provincia", "operador": "en", "valores": ["Salta", "Jujuy"]}].
  Operadores: =, !=, mayor_que, menor_que, >=, <=, contiene y en. La igualdad y
  \`contiene` no distinguen mayúsculas ni acentos (en tablas de más de un millón de
  filas, sí: ahí la respuesta dice en `filtros_aplicados` qué se buscó tal cual).
\- `orden`: "asc" (por defecto: primero lo más viejo) o "desc" (primero lo más
  reciente), por fecha. Para el último dato de una serie, pedí "desc".
\- `limite`: 1 a 500 filas. Si hay más, la respuesta lo dice y da el `offset` de la
  página siguiente (hasta 10.000).
\- `columna_fecha`: opcional, otra columna de fecha para `desde`/`hasta` y el orden.
Si ninguna fila cumple los filtros, la respuesta dice qué valores existen.
No descuenta preguntas.

Input parameters:

- `columna_fecha`
- `columnas`
- `desde`
- `filtros`
- `hasta`
- `limite` (integer)
- `offset` (integer)
- `orden`
- `tabla` (string, required)

Output parameters:

- `result` (string)

### `agregar_datos` (~506 tokens)

Calcular totales y rankings sobre una tabla de OpenArg

Calcula en la base una suma, promedio, conteo, mínimo o máximo, opcionalmente agrupado.

Usala SIEMPRE que necesites un total, un promedio, un conteo, un mínimo/máximo o un
ranking, en vez de traer filas con `obtener_datos` y hacer la cuenta vos: es exacta,
no tiene el tope de 500 filas y gasta muchos menos tokens.
\- `operacion`: "suma", "promedio", "conteo", "minimo" o "maximo".
\- `columna`: la que se suma/promedia/etc. (nombres exactos de `describir_tabla`); no
  va con "conteo", que cuenta filas (si la mandás, da error). Las columnas de texto
  con números se leen según su formato (1.234,5 o 1,234.5); si el formato es
  ambiguo, no calcula y lo dice.
\- `agrupar_por`: hasta 3 columnas, p. ej. ["jurisdiccion_desc"] para un ranking.
\- `filtros`, `desde`, `hasta`, `columna_fecha`: como en `obtener_datos` (hasta 6 filtros).
\- `ordenar_por`: "valor" (por defecto, para rankings) o una columna de `agrupar_por`
  (p. ej. el año, para una serie). `orden`: "desc" (por defecto) o "asc".
\- `limite`: grupos a devolver, 1 a 200.
\- `ponderar_por`: la columna de ponderación de una encuesta (con "conteo" da la
  población estimada, no la cantidad de filas de la muestra).
La respuesta dice sobre cuántas filas se calculó (`filas_usadas`, de todos los
grupos) y si hay más grupos que `limite`. Si ninguna fila cumple los filtros no hay
valor: dice qué valores existen. No descuenta preguntas.

Input parameters:

- `agrupar_por`
- `columna`
- `columna_fecha`
- `desde`
- `filtros`
- `hasta`
- `limite` (integer)
- `operacion` (string, required)
- `orden` (string)
- `ordenar_por`
- `ponderar_por`
- `tabla` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/org-openarg-datos-publicos/mcp#diagnostics

## Score history

- 2026-11-05: 81
- 2026-11-04: 81
- 2026-11-03: 81
- 2026-11-02: 81
- 2026-11-01: 81
- 2026-10-31: 81
- 2026-10-30: 81
- 2026-10-29: 81
- 2026-10-28: 80
- 2026-10-27: 80
- 2026-10-26: 79
- 2026-10-25: 79
- 2026-10-24: 78
- 2026-10-23: 78
- 2026-10-22: 77
- 2026-10-21: 77
- 2026-10-20: 76
- 2026-10-19: 76
- 2026-10-18: 75
- 2026-10-17: 75
- 2026-10-16: 74
- 2026-10-15: 74
- 2026-10-14: 74
- 2026-10-13: 73
- 2026-10-12: 73
- 2026-10-10: 72
- 2026-10-07: 73
- 2026-10-04: 72
- 2026-10-03: 72
- 2026-10-02: 71

## Common questions

### What is the OpenArg — Argentina public data MCP server?

OpenArg — Argentina public data is an MCP server listed in the public MCP registry as org.openarg/datos-publicos. Argentina's official public data (INDEC, BCRA, 38 portals): search, read tables, cited answers. This page covers its hosted endpoint (https://mcp.openarg.org/mcp).

### Is the OpenArg — Argentina public data MCP server safe to use?

OpenArg — Argentina public data scores 81 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the OpenArg — Argentina public data MCP server expose?

OpenArg — Argentina public data exposes 6 tools: consultar_datos_publicos, listar_fuentes, buscar_datasets, describir_tabla, obtener_datos, agregar_datos. Their descriptions and schemas cost roughly 1,518 tokens of context every time the server is loaded.

### Does the OpenArg — Argentina public data MCP server require authentication?

No. We connected to OpenArg — Argentina public data without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the OpenArg — Argentina public data MCP server still maintained?

OpenArg — Argentina public data is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the OpenArg — Argentina public data MCP server?

VerifyMCP ran 12 checks on OpenArg — Argentina public data, covering TLS certificate, Authorization, HTTPS, HSTS header and 8 more. One item could not be completed, a gap on our side rather than a finding about OpenArg — Argentina public data: Judged manipulation. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://mcp.openarg.org/mcp
- Authorisation metadata: https://mcp.openarg.org/.well-known/oauth-protected-resource/mcp
- Repository: https://github.com/colossus-lab/openarg-mcp
- Website: https://mcp.openarg.org/
- Changelog RSS feed: https://verifymcp.io/servers/org-openarg-datos-publicos/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/org-openarg-datos-publicos/mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/org-openarg-datos-publicos/mcp.json
- HTML version of this page: https://verifymcp.io/servers/org-openarg-datos-publicos/mcp