Get detailed information about specific endpoints
AI agents call get-endpoints to retrieve information from Swagger MCP Server 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 endpoint information from Swagger/OpenAPI definitions. It is informational in nature, returning documentation and endpoint details without creating, modifying, deleting, or executing any operations. The action is read-only and has minimal blast radius even if an AI agent calls it repeatedly or with unexpected arguments.
From the tool's definition Tool name 'get-endpoints' and description 'Get detailed information about specific endpoints' indicates retrieval of metadata/documentation about API endpoints with no side effects.
Attacks that exploit this kind of access
Get detailed information about specific endpoints. It is categorised as a Read tool in the Swagger MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Swagger MCP Server MCP server in PolicyLayer and add a rule for get-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 Swagger MCP Server. Nothing to install.
get-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 get-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 get-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.
get-endpoints is provided by the Swagger MCP Server MCP server (marcin-sucharski/swagger-mcp-server). 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 →