Calculate aggregated metrics and statistics across spans. Use this tool to: - Get latency percentiles for endpoints (p50, p95, p99) - Calculate error rates by endpoint - Get request counts over time - Compare performance across environments Examples: - Endpoint latency: groupBy = [
AI agents call aggregate_spans to retrieve information from Tusk Drift MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs statistical aggregation and analysis on application traffic data already captured by Tusk Drift. It retrieves metrics, calculates percentiles, and provides comparative analysis—all read-only operations with no side effects on the underlying data or systems.
From the tool's definition The tool description explicitly states it 'Calculate[s] aggregated metrics and statistics across spans' and all use cases are read-only analytics: 'Get latency percentiles', 'Calculate error rates', 'Get request counts', 'compare performance'.
Documented attack patterns abuse exactly the kind of access aggregate_spans gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tusk Drift MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for aggregate_spans:
{
"version": "1",
"default": "deny",
"tools": {
"aggregate_spans": {}
}
}aggregate_spans is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Calculate aggregated metrics and statistics across spans. Use this tool to: - Get latency percentiles for endpoints (p50, p95, p99) - Calculate error rates by endpoint - Get request counts over time - Compare performance across environments Examples: - Endpoint latency: groupBy = [. It is categorised as a Read tool in the Tusk Drift MCP MCP Server, which means it retrieves data without modifying state.
Register the Tusk Drift MCP server in PolicyLayer and add a rule for aggregate_spans: 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 Tusk Drift MCP. Nothing to install.
aggregate_spans 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 aggregate_spans 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 aggregate_spans. 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.
aggregate_spans is provided by the Tusk Drift MCP server (use-tusk/drift-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tusk Drift MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Tusk Drift MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.