Use this tool ONLY to find and analyze recurring stack traces in your application. It aggregates similar stack traces, providing statistics like the number of occurrences and the number of affected users. DO NOT use this tool for general error searches or to view individual error logs. For querie...
AI agents call list_group_stats to retrieve information from Observability without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool's purpose is to query and analyze observability data (stack trace statistics and user impact metrics). It retrieves and presents aggregated information without creating, modifying, deleting, or executing any operations. This is a standard Read category operation typical of observability/monitoring platforms.
From the tool's definition Tool description explicitly states it 'find and analyze recurring stack traces' and 'aggregates similar stack traces, providing statistics like the number of occurrences and the number of affected users.' These are data retrieval and aggregation operations…
Attacks that exploit this kind of access
Use this tool ONLY to find and analyze recurring stack traces in your application. It aggregates similar stack traces, providing statistics like the number of occurrences and the number of affected users. DO NOT use this tool for general error searches or to view individual error logs. For queries asking to. It is categorised as a Read tool in the Observability MCP Server, which means it retrieves data without modifying state.
Register the Observability MCP server in PolicyLayer and add a rule for list_group_stats: 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 Observability. Nothing to install.
list_group_stats 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_group_stats 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_group_stats. 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_group_stats is provided by the Observability MCP server (@google-cloud/observability-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 →