Returns all API endpoints from the saved OpenAPI spec, grouped by their tag (e.g.
AI agents call available-api-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 only reads and returns documentation/metadata about API endpoints from an OpenAPI spec. It has no side effects, does not execute any requests, and does not modify any data. It is purely an informational retrieval operation.
From the tool's definition Returns all API endpoints from the saved OpenAPI spec, grouped by their tag
Attacks that exploit this kind of access
Returns all API endpoints from the saved OpenAPI spec, grouped by their tag (e.g. 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 available-api-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.
available-api-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 available-api-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 available-api-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.
available-api-endpoints is provided by the Swagger MCP Server MCP server (nksmkj7/swagger-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 →