AI agents call get_endpoint to retrieve information from Mcp Docs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool exposes pre-existing API documentation and schema metadata. Reading OpenAPI specs poses no direct risk—it is purely informational querying. An agent cannot cause side effects by retrieving endpoint specifications, though such information could inform subsequent malicious actions if combined with other tools. The low severity reflects that this is foundational read-only documentation access.
From the tool's definition Tool retrieves OpenAPI operation objects and documentation (parameters, request body, responses, security) without modifying or executing anything. Verb 'Get' and action 'retrieve' indicate data retrieval only.
Attacks that exploit this kind of access
Get the full OpenAPI operation object (parameters, request body, responses, security) for a single REST endpoint. It is categorised as a Read tool in the Mcp Docs MCP Server, which means it retrieves data without modifying state.
Register the Mcp Docs MCP server in PolicyLayer and add a rule for get_endpoint: 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 Docs. Nothing to install.
get_endpoint 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_endpoint 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_endpoint. 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_endpoint is provided by the Mcp Docs MCP server (prosodyai/mcp-docs). 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 →