Garita MCP

Detectar instrucciones escondidas en descripciones de herramientas (Garita Escudo)

detect_poisoned_tool_descriptions

Analiza la(s) descripción(es) de una o más herramientas MCP en busca de instrucciones ocultas o inyectadas ("tool poisoning" / inyección de prompt): caracteres invisibles, esteganografía Unicode, homoglifos (letras de otro alfabeto mezcladas), entidades HTML en capas, bloques de pseudo-instrucción escondidos (, comentarios), instrucciones para ocultar la acción al usuario, para manipular OTRA herramienta, para redirigir/copiar datos a otro destino, o para decodificar y seguir un texto codificado. Devuelve un puntaje de 0 a 100 y el detalle de cada señal encontrada, con el fragmento de texto donde apareció. Es un chequeo distinto y complementario a audit_mcp_server (que revisa el esquema/anotaciones del manifiesto, no el contenido semántico del texto) — úsalo antes de confiar en la descripción de una herramienta MCP nueva o desconocida. Requiere una llave de acceso válida (usos gratis o créditos) — ver POST /crear-llave.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "detect_poisoned_tool_descriptions"
  }
}

Input Schema

Name	Required	Description	Default
`text`	No	Alternativa a "manifest": una descripción de herramienta suelta, en texto plano.
`manifest`	No	Manifiesto MCP { serverInfo, tools: [...] }, un arreglo de herramientas, o una sola herramienta { name, description }.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 10, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden and does most of it: it discloses the return shape (0-100 score plus per-signal detail with the offending text fragment) and the auth requirement (valid access key, free uses or credits, key endpoint). It does not state side-effect-free/read-only status or rate/cost limits beyond the free-uses mention, which keeps it below a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and threat scope are front-loaded in the first sentence, followed by return behavior, sibling differentiation, and prerequisites in a logical order. The long enumeration with nested parentheticals makes it a dense single block, but each clause defines scope rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description compensates by explaining the score-plus-evidence return format. With only two optional parameters, 100% schema coverage, and the auth prerequisite plus sibling boundary all disclosed, an agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents both `text` and `manifest`. The description only implies the input surface with "descripción(es) de una o más herramientas," which loosely maps to the single-description vs. multi-tool manifest split but never explains the alternative or precedence between them. Baseline 3 applies since the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Analiza la(s) descripción(es) de una o más herramientas MCP en busca de instrucciones ocultas o inyectadas" states a specific verb and resource, then enumerates the exact threat classes (invisible characters, Unicode steganography, homoglyphs, layered HTML entities, hidden <IMPORTANT> blocks, exfiltration instructions, encoded payloads). It explicitly contrasts itself with audit_mcp_server, so an agent can distinguish it from the nearest sibling without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Es un chequeo distinto y complementario a audit_mcp_server (que revisa el esquema/anotaciones del manifiesto, no el contenido semántico del texto)" names the alternative and draws the boundary precisely. "Úsalo antes de confiar en la descripción de una herramienta MCP nueva o desconocida" gives an explicit trigger condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Garita MCP tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?