Search cached endpoints for a previously detected OpenAPI spec using a server-side semantic-style scorer over endpoint metadata and schema field names.
AI agents call search_endpoints to retrieve information from MCP OpenAPI Discovery without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation as it only retrieves and queries information about existing cached endpoints. It does not create, modify, delete, or execute any operations. The semantic scoring is performed locally over cached data for discovery purposes. No side effects or state changes occur.
From the tool's definition Tool searches and retrieves cached endpoint metadata using semantic scoring. The description explicitly indicates it 'Search[es] cached endpoints' and performs scoring over 'endpoint metadata and schema field names' - purely read operations with no…
Attacks that exploit this kind of access
Search cached endpoints for a previously detected OpenAPI spec using a server-side semantic-style scorer over endpoint metadata and schema field names. It is categorised as a Read tool in the MCP OpenAPI Discovery MCP Server, which means it retrieves data without modifying state.
Register the MCP OpenAPI Discovery 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 MCP OpenAPI Discovery. 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 MCP OpenAPI Discovery MCP server (rekl0w/mcp-openapi-discovery). 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 →