Fuzzy-search the API spec by keyword. Use this when you don
AI agents call search_endpoints 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 performs a read-only search operation against the API specification. It retrieves matching endpoints based on keyword matching but does not create, modify, execute, delete, or trigger any external actions. The fuzzy search is a discovery mechanism with no side effects.
From the tool's definition Tool name 'search_endpoints' and description 'Fuzzy-search the API spec by keyword' indicate a query/search operation that retrieves data from the API specification without modifying or executing anything.
Documented attack patterns abuse exactly the kind of access search_endpoints 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 search_endpoints:
{
"version": "1",
"default": "deny",
"tools": {
"search_endpoints": {}
}
}search_endpoints 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.
Fuzzy-search the API spec by keyword. Use this when you don. 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 search_endpoints: 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.
search_endpoints 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 search_endpoints 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 search_endpoints. 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.
search_endpoints 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.