Search for API endpoints by query, method, or tags
AI agents call search_endpoints to retrieve information from Sufetch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries API endpoint metadata and documentation to help users discover available endpoints. It performs no modifications, deletions, or external operations—it only retrieves and presents information from the OpenAPI schemas. The low severity reflects that misuse would only expose documentation that is typically public or intended for API exploration.
From the tool's definition Tool name 'search_endpoints' and description 'Search for API endpoints by query, method, or tags' indicate data retrieval without modification.
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 Sufetch, 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.
Search for API endpoints by query, method, or tags. It is categorised as a Read tool in the Sufetch MCP Server, which means it retrieves data without modifying state.
Register the Sufetch 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 Sufetch. 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 Sufetch MCP server (productdevbook/sufetch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Sufetch, 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.
7 Sufetch tools catalogued and risk-classified — across an index of 43,000+ MCP servers.