Gets detailed information about a specific agent, including its instructions/description.
AI agents call describeAgent to retrieve information from Mcp Agent Proxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata and configuration details about an agent without modifying, executing, or deleting anything. It is purely informational with minimal blast radius if misused by an AI agent—at worst it could expose agent instructions or internal details, but cannot cause data loss, execution of arbitrary code, or financial harm.
From the tool's definition The tool description explicitly states it 'Gets detailed information about a specific agent' which is a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access describeAgent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Agent Proxy, and nothing reaches the server without passing your rules. This is the rule we recommend for describeAgent:
{
"version": "1",
"default": "deny",
"tools": {
"describeAgent": {}
}
}describeAgent is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Gets detailed information about a specific agent, including its instructions/description. It is categorised as a Read tool in the Mcp Agent Proxy MCP Server, which means it retrieves data without modifying state.
Register the Mcp Agent Proxy MCP server in PolicyLayer and add a rule for describeAgent: 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 Agent Proxy. Nothing to install.
describeAgent 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 describeAgent 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 describeAgent. 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.
describeAgent is provided by the Mcp Agent Proxy MCP server (mashh-lab/mcp-agent-proxy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Agent Proxy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Mcp Agent Proxy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.