LATIDIA · Ciberseguridad
Cuando los nombres de las herramientas no son identidades: medición de la vinculación errónea de proveedores en agentes de IA basados en MCP
arXiv:2611.21577v1 Tipo de anuncio: nuevo Resumen: Las aplicaciones de modelos de lenguaje grande (LLM) actúan cada vez más como agentes que seleccionan e invocan herramientas externas. El Protocolo de Contexto del Modelo (MCP) estandariza esta interacción al
WhatsApp ↗Telegram ↗
La noticia
arXiv:2611.21577v1 Announce Type: new Abstract: Large language model (LLM) applications increasingly act as agents that select and invoke external tools. The Model Context Protocol (MCP) standardizes this interaction by allowing clients to compose tools advertised by multiple servers. However, tool metadata used for discovery and selection is not, by itself, necessarily bound to a verified provider identity. This paper studies this gap as tool-provider misbinding: a failure in which a request intended for a legitimate provider is instead resolved to an attacker-controlled tool. The attacker does not compromise the host, LLM, legitimate server, or network channel; it only operates another MCP server that advertises tools with chosen metadata. We formulate