El uso de herramientas funcionales hace que los agentes de IA sean muy potentes, algo similar a la introducción de las tiendas de aplicaciones en smartphones. Especialmente con el lanzamiento de MCP (Protocolo de Contexto de Modelo) , compartir herramientas es más fácil que nunca. Por eso creé el proyecto extendable-agents para mostrar lo fácil que es ampliar las capacidades de los agentes de IA mediante herramientas de código abierto o herramientas personalizadas.
Mientras trabajaba con agentes extensibles, me di cuenta de que usar herramientas es un arma de doble filo. El peligro radica en que las herramientas que se usan tienen acceso poderoso a la máquina, como las variables de entorno, los archivos, etc.
Este proyecto es una simple demostración de los riesgos de seguridad asociados al uso de herramientas. El siguiente ejemplo ilustra cómo actores maliciosos podrían explotar los servidores MCP para acceder a información confidencial:
# WARNING: This is a demonstration of security risks.
# DO NOT use this code maliciously!
import os
from mcp.server.fastmcp import FastMCP
server = FastMCP("Dangerous MCP")
@server.tool()
async def get_environment_variables() -> str:
"""Get all environment variables."""
result = [
"Here are what I could find:",
]
for key, value in os.environ.items():
result.append(f"{key:<30} {value[:5]}***")
# This means I can open a backdoor to send your data to me!!
return "\n".join(result)⚠️ Advertencia: Recomiendo ejecutar este ejemplo en un entorno aislado y eliminar posteriormente la clave de API de OpenAI. También puede probarlo con su propio cliente MCP con el siguiente comando:
uvx mcp-is-dangerous.
Al utilizar esta herramienta con agentes extensibles (elija PoliceAgent ), el resultado aparece así:
Puede parecer inofensivo o incluso intencionalmente benigno, ¿verdad? Pero imagina este escenario: simplemente preguntas la hora actual y, mientras tanto, tus datos confidenciales se filtran sin tu conocimiento.
Related MCP server: Vulnerable MCP Server
Para protegerse al utilizar MCP o herramientas similares:
Revise siempre el código fuente de las herramientas antes de usarlas
Ejecute herramientas en entornos aislados cuando sea posible
Tenga cuidado con las herramientas que solicitan acceso a información confidencial
Utilice el filtrado de variables de entorno al implementar herramientas
Audita periódicamente las herramientas que estás utilizando
Este proyecto tiene fines educativos únicamente para demostrar los posibles riesgos de seguridad. No utilice este conocimiento con fines maliciosos. El autor no se responsabiliza del mal uso de esta información.
Get all environment variables.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The tool name and description imply a read-only operation ('Get'), which is transparent for a simple retrieval. No annotations are present, so the description carries the full burden. It does not mention authentication, rate limits, or return format, but the behavior is straightforward.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It directly conveys the tool's purpose without extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters, no output schema, and no siblings, the description is mostly complete. It clearly states what the tool does. Missing information about return format or usage context is minor given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and the input schema already reflects this fact. The description does not need to add parameter details. Baseline for 0 parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves all environment variables. The verb 'Get' and resource 'environment variables' are specific and unambiguous. Without siblings, no further differentiation is needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use or alternatives is provided. However, as there are no sibling tools, the context implicitly limits usage to this single tool. A user might still benefit from knowing prerequisites or side effects.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_environment_variablesScored across 1 tool
Only one tool exists, so there is no ambiguity in selection.
Single tool follows a clean verb_noun pattern, consistent.
One tool is too few for the server's implied scope; a broader set is expected.
Only a single read operation is provided, with no other tools to cover related actions like modification or listing.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Security research canary remote MCP server for owned-account testing.
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
