AI agents call find_endpoint_by_keyword to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about Swagger/OpenAPI endpoints matching a keyword. It queries existing API specification data without modifying, executing, or deleting anything. The operation is purely informational with no side effects. Severity is low because endpoint discovery poses minimal risk even in adversarial contexts.
From the tool's definition Tool description states 'Find Swagger paths containing a keyword' - a search/lookup operation with no modification or execution capabilities. The verb 'find' and action of searching paths are characteristic of read operations.
Attacks that exploit this kind of access
Find Swagger paths containing a keyword. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for find_endpoint_by_keyword: 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. Nothing to install.
find_endpoint_by_keyword 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 find_endpoint_by_keyword 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 find_endpoint_by_keyword. 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.
find_endpoint_by_keyword is provided by the MCP server (victormyschik/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 →