AI agents call find_agent to retrieve information from Aiprox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries an agent registry and retrieves matching results based on search criteria. It does not create, modify, delete, or execute any operations. While the server context mentions payment orchestration and hiring agents, this specific tool only performs discovery/search, which is a Read operation. The low severity reflects that querying a registry poses minimal risk even if misused by an agent.
From the tool's definition Tool description states it will 'return the most suitable registered agent' — a pure query/lookup operation with no side effects. The verb 'find' and 'return' indicate data retrieval only.
Attacks that exploit this kind of access
Find the best agent for a specific task. Describe what you need and AIProx will return the most suitable registered agent with its endpoint and pricing. It is categorised as a Read tool in the Aiprox MCP Server, which means it retrieves data without modifying state.
Register the Aiprox MCP server in PolicyLayer and add a rule for find_agent: 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 Aiprox. Nothing to install.
find_agent 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 find_agent 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 find_agent. 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.
find_agent is provided by the Aiprox MCP server (unixlamadev-spec/aiprox-mcp). 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 →