get_metrics
Aggregate request metrics for this project over a time window — volume, error rate and p50/p95/p99 latency, bucketed for charting. By default the series cover inbound requests; pass targetId to slice over one outbound target's per-attempt rows instead (answers "which target is degraded?"); pass e...
This record as markdown: /tools/dev-echorelay-management/get-metrics.md
What get_metrics does on EchoRelay
AI agents call get_metrics to retrieve information from EchoRelay without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
window | string | — | Time horizon. Defaults to "day". "week"/"month" require a paid plan; otherwise the server returns "day" with planGated=true. |
targetId | string | — | Optional outbound target UUID (from get_endpoint targets). When set, the series aggregate the per-attempt rows for that target instead of the project-wide inbou |
endpointId | string | — | Optional endpoint UUID (from list_endpoints / get_endpoint). When set, the series aggregate inbound request rows for that endpoint only. Mutually exclusive with |
Parameters from the server's own tool schema.
Why get_metrics is rated Low
get_metrics queries and returns observability data without side effects. It supports filtering and time-windowing but performs only read operations on historical metrics. The mention of subscription tiers affects data granularity but does not constitute a financial transaction or state change. This is a pure data retrieval tool with minimal blast radius if misused by an agent.
From the tool's definition Tool retrieves aggregate metrics data (volume, error rate, latency) over time windows with optional filtering by targetId or endpointId. The description uses retrieval language: 'Aggregate request metrics', 'see', 'slice over'.
Attacks that exploit this kind of access
The rule that runs get_metrics safely
PolicyLayer is an MCP gateway: it sits between your AI agents and EchoRelay, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_metrics, this is the rule to start with:
get_metrics is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect EchoRelay, apply this rule, and every get_metrics call is checked against it from then on.
Questions about get_metrics
Aggregate request metrics for this project over a time window — volume, error rate and p50/p95/p99 latency, bucketed for charting. By default the series cover inbound requests; pass targetId to slice over one outbound target's per-attempt rows instead (answers "which target is degraded?"); pass endpointId to slice over inbound rows for a single endpoint (answers "is this endpoint receiving traffic / erroring?"). Pass at most one of targetId / endpointId. Free plans see "hour" and "day"; "week" and "month" require an active paid subscription on the project owner and are silently downgraded to "day" otherwise (the response includes planGated: true when that happens). Returns {window, requestedWindow, planGated, scope, targetId?, endpointId?, bucketSeconds, buckets[], volume[], errors[], p50[], p95[], p99[], totalVolume, totalErrors, errorRate} — series arrays are dense (one point per bucket, zero-filled when no traffic). It is categorised as a Read tool in the EchoRelay MCP Server, which means it retrieves data without modifying state.
get_metrics accepts 3 parameters: window, targetId, endpointId. The full parameter table on this page comes from the server's own tool schema.
Register the EchoRelay 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 EchoRelay. 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 EchoRelay MCP server (https://mcp.echorelay.dev). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on EchoRelay, and thousands of servers like it.
This server
Across the catalogue