Busca hoteles en ciudades colombianas. Requiere Soulprint score >= 40 para datos de contacto.
AI agents call viajes_buscar_hotel to retrieve information from Mcp Colombia without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves hotel information from Colombian travel services. It performs a search operation (buscar = search) that returns data without modifying, creating, deleting, or executing external operations. The Soulprint score gate is an access control mechanism, not indicative of a different operation category.
From the tool's definition Tool name "viajes_buscar_hotel" and description "Busca hoteles en ciudades colombianas" (searches hotels in Colombian cities) indicates data retrieval.
Attacks that exploit this kind of access
Busca hoteles en ciudades colombianas. Requiere Soulprint score >= 40 para datos de contacto. It is categorised as a Read tool in the Mcp Colombia MCP Server, which means it retrieves data without modifying state.
Register the Mcp Colombia MCP server in PolicyLayer and add a rule for viajes_buscar_hotel: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Colombia. Nothing to install.
viajes_buscar_hotel is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the viajes_buscar_hotel rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for viajes_buscar_hotel. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
viajes_buscar_hotel is provided by the Mcp Colombia MCP server (manuelariasfz/mcp-colombia). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →