list_operations
AI agents call list_operations to retrieve information from OpenAPI MCP Gateway without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
List/enumerate operations is a read-only information retrieval action with no side effects. Confidence reduced slightly due to empty description, but the semantic meaning of 'list' and context as a gateway tool for introspection supports Read category. Severity is low as merely enumerating available API operations poses minimal risk.
From the tool's definition Tool name 'list_operations' indicates retrieval of available operations; no description provided but naming convention and pairing with 'call_operation' and 'get_operation' suggest this lists/queries operations without modification.
Attacks that exploit this kind of access
list_operations. It is categorised as a Read tool in the OpenAPI MCP Gateway MCP Server, which means it retrieves data without modifying state.
Register the OpenAPI MCP Gateway MCP server in PolicyLayer and add a rule for list_operations: 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 MCP Gateway. Nothing to install.
list_operations 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 list_operations 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 list_operations. 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.
list_operations is provided by the OpenAPI MCP Gateway MCP server (mroops0111/openapi-mcp-gateway). 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 →