AI agents call get-api-endpoint-schema to retrieve information from Openapi 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 schema metadata about an API endpoint. It does not modify, execute, or delete anything; it simply reads and returns information. The action is informational only, making it a Read category tool. Severity is low because schema retrieval has minimal blast radius—it cannot cause harm even if misused by an agent, as it only exposes structural information about endpoints.
From the tool's definition Tool name is 'get-api-endpoint-schema' and description states it 'Get[s] the JSON schema for a specified API endpoint' — this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the JSON schema for a specified API endpoint. It is categorised as a Read tool in the Openapi MCP Server, which means it retrieves data without modifying state.
Register the Openapi MCP server in PolicyLayer and add a rule for get-api-endpoint-schema: 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 Openapi. Nothing to install.
get-api-endpoint-schema 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-api-endpoint-schema 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-api-endpoint-schema. 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-api-endpoint-schema is provided by the Openapi MCP server (@ivotoby/openapi-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 →