AI agents call ops_list_components to retrieve information from Ops without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries component metadata from Statuspage without creating, modifying, deleting, or executing any operations. It is a pure information-retrieval utility used to support other operations by resolving component identifiers. The blast radius of misuse is minimal—an agent could discover component names/IDs but cannot alter system state or cause operational impact.
From the tool's definition Tool name 'list' and description 'List all Statuspage components' indicate data retrieval with no modification or side effects. The purpose is to 'resolve names to IDs', a lookup operation.
Attacks that exploit this kind of access
List all Statuspage components (resolve names to IDs). It is categorised as a Read tool in the Ops MCP Server, which means it retrieves data without modifying state.
Register the Ops MCP server in PolicyLayer and add a rule for ops_list_components: 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 Ops. Nothing to install.
ops_list_components 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 ops_list_components 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 ops_list_components. 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.
ops_list_components is provided by the Ops MCP server (sydney-robotics-academy/ops-mcp). 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 →