export_metrics
AI agents call export_metrics to retrieve information from Observability MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'export_metrics' suggests retrieving or exporting collected metrics data, which is a read operation in an observability context. However, the description is empty, so classification is based solely on the name and server context. 'Export' could imply writing to an external destination, but in observability systems it typically means reading/pulling metrics for consumption.
From the tool's definition Tool name 'export_metrics' and server context focused on monitoring/observability with Prometheus and OpenTelemetry metrics collection
Attacks that exploit this kind of access
export_metrics. It is categorised as a Read tool in the Observability MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Observability MCP Server MCP server in PolicyLayer and add a rule for export_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 Observability MCP Server. Nothing to install.
export_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 export_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 export_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.
export_metrics is provided by the Observability MCP Server MCP server (sandraschi/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 →