Keyword search across operationId, path, summary, description and tags. Returns the best-matching
AI agents call search_endpoints to retrieve information from Tossinvest Openapi 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 information about API endpoints without modifying, executing, or deleting any data. It is purely informational, helping users discover available endpoints. The severity is low because misuse would only result in retrieving documentation, posing no risk to data integrity or system operations.
From the tool's definition Tool description states it performs "Keyword search across operationId, path, summary, description and tags" and "Returns the best-matching" results.
Attacks that exploit this kind of access
Keyword search across operationId, path, summary, description and tags. Returns the best-matching. It is categorised as a Read tool in the Tossinvest Openapi MCP Server, which means it retrieves data without modifying state.
Register the Tossinvest Openapi 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 Tossinvest Openapi. 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 Tossinvest Openapi MCP server (jeongseongmok/tossinvest-openapi-mcp). 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 →