Get observability metrics — success rates, latency, top errors, breakdown by tool and target.
AI agents call metrics to retrieve information from SelfHeal MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports aggregated observability data (success rates, latency statistics, error summaries). It has no side effects—it reads existing metrics without creating, modifying, deleting, or executing operations. The blast radius of misuse is minimal; an attacker could only gain visibility into system performance characteristics, not affect actual operations or data.
From the tool's definition Tool name 'metrics' and description 'Get observability metrics — success rates, latency, top errors, breakdown by tool and target' indicate retrieval and querying of monitoring/observability data with no state-modifying operations.
Attacks that exploit this kind of access
Get observability metrics — success rates, latency, top errors, breakdown by tool and target. It is categorised as a Read tool in the SelfHeal MCP MCP Server, which means it retrieves data without modifying state.
Register the SelfHeal MCP server in PolicyLayer and add a rule for 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 SelfHeal MCP. Nothing to install.
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 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 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.
metrics is provided by the SelfHeal MCP server (selfheal-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 →