Return request metrics (per-endpoint latency, success/error counts).
AI agents call get_metrics to retrieve information from Pypi:mcp Cn Commerce without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves operational metrics (latency, success/error counts) for monitoring purposes. It has no side effects, does not modify any state, and does not execute code or trigger external operations. It is purely a data retrieval operation consistent with the server's read-only design. Misuse would result in only information disclosure about API performance, which is low-impact.
From the tool's definition Tool name 'get_metrics' and description 'Return request metrics (per-endpoint latency, success/error counts)' indicate retrieval of monitoring/observability data. The server is explicitly described as providing 'read-only access' to business data.
Attacks that exploit this kind of access
Return request metrics (per-endpoint latency, success/error counts). It is categorised as a Read tool in the Pypi:mcp Cn Commerce MCP Server, which means it retrieves data without modifying state.
Register the Pypi:mcp Cn Commerce MCP server in PolicyLayer and add a rule for get_metrics: 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 Pypi:mcp Cn Commerce. Nothing to install.
get_metrics 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_metrics 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_metrics. 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_metrics is provided by the Pypi:mcp Cn Commerce MCP server (tonywang-hub/mcp-cn-commerce). 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 →