operationIdの詳細（paths/method/要約/原文）を返す
AI agents call describe_api to retrieve information from ACOMO MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a schema inspection/metadata retrieval tool. It queries and returns information about API operations (paths, methods, summaries) but does not execute operations, modify data, or trigger side effects. It falls squarely in the Read category as it only retrieves descriptive information about available API endpoints.
From the tool's definition Tool name 'describe_api' and description 'returns details (paths/method/summary/original text) of operationId' indicate retrieval of API schema/metadata information without modification or execution.
Attacks that exploit this kind of access
operationIdの詳細（paths/method/要約/原文）を返す. It is categorised as a Read tool in the ACOMO MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ACOMO MCP Server MCP server in PolicyLayer and add a rule for describe_api: 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 ACOMO MCP Server. Nothing to install.
describe_api 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 describe_api 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 describe_api. 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.
describe_api is provided by the ACOMO MCP Server MCP server (progress-all/acomo-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 →