AI agents call get_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 and retrieves metadata about registered agents from a registry. It performs a lookup operation that returns information without side effects. While the server context mentions payment rails and agent orchestration, this specific tool only retrieves agent details. No data is modified, deleted, executed, or financial transactions are initiated by get_agent itself.
From the tool's definition Tool description states 'Get full details for a specific agent' and 'Returns endpoint, pricing, payment rail, capabilities, and models' — these are read-only retrieval operations with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Get full details for a specific agent in the AIProx registry by name. Returns endpoint, pricing, payment rail, capabilities, and models. 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 get_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.
get_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 get_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 get_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.
get_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 →