AI agents call get_openapi 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 retrieves and returns API specification metadata. It does not execute queries against live systems, modify data, delete resources, or commit financial transactions. It is a read-only documentation lookup, analogous to 'get' or 'fetch' operations. Low severity because misuse exposes only technical documentation, not sensitive user data or system access.
From the tool's definition Tool name is 'get_openapi' and description states 'Return the full bundled OpenAPI 3 spec' — a retrieval operation with no side effects. The note 'Use sparingly' indicates it fetches static documentation/schema data.
Attacks that exploit this kind of access
Return the full bundled OpenAPI 3 spec for the ProsodyAI REST API. Use sparingly — prefer. 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_openapi: 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_openapi 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_openapi 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_openapi. 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_openapi 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 →