Returns the full OpenAPI schema for a single endpoint: parameters, request body schema with types and required fields,
AI agents call describe_endpoint to retrieve information from Rest Api without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries endpoint documentation from an OpenAPI specification. It performs introspection only—examining an endpoint's structure, parameters, and request body definitions—without executing requests, modifying data, or triggering external operations. The blast radius is minimal since it only exposes structural metadata that would typically be public API documentation.
From the tool's definition Tool description states it 'Returns the full OpenAPI schema for a single endpoint' with parameters and schema information. The verb 'Returns' and the nature of retrieving schema metadata indicate data retrieval with no side effects.
Documented attack patterns abuse exactly the kind of access describe_endpoint gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rest Api, and nothing reaches the server without passing your rules. This is the rule we recommend for describe_endpoint:
{
"version": "1",
"default": "deny",
"tools": {
"describe_endpoint": {}
}
}describe_endpoint 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.
Returns the full OpenAPI schema for a single endpoint: parameters, request body schema with types and required fields,. It is categorised as a Read tool in the Rest Api MCP Server, which means it retrieves data without modifying state.
Register the Rest Api MCP server in PolicyLayer and add a rule for describe_endpoint: 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 Rest Api. Nothing to install.
describe_endpoint 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 describe_endpoint 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 describe_endpoint. 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.
describe_endpoint is provided by the Rest Api MCP server (muhammed-abdelghany/rest_api_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rest Api, 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 Rest Api tools catalogued and risk-classified — across an index of 43,000+ MCP servers.