selfheal_metrics

Get SelfHeal proxy metrics — success rates, latency, top errors

Server SelfHeal MCP selfheal-mcp
Category Read
Risk class Low
Parameters 00 required

What selfheal_metrics does on SelfHeal MCP

AI agents call selfheal_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.

Why selfheal_metrics needs a policy

This tool queries and returns observability/monitoring data about the SelfHeal proxy's performance. It has no side effects, does not modify state, execute code, or perform destructive actions. It is purely informational. The blast radius of an AI agent misusing this is minimal — at worst, excessive metric queries could impact logging/monitoring systems, but the tool itself is read-only.

From the tool's definition Tool name 'selfheal_metrics' and description 'Get SelfHeal proxy metrics' — explicitly a retrieval operation. Described as retrieving 'success rates, latency, top errors' with no modification, deletion, or execution capabilities.

Questions about selfheal_metrics

What does the selfheal_metrics tool do? +

Get SelfHeal proxy metrics — success rates, latency, top errors. It is categorised as a Read tool in the SelfHeal MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on selfheal_metrics? +

Register the SelfHeal MCP server in PolicyLayer and add a rule for selfheal_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.

What risk level is selfheal_metrics? +

selfheal_metrics is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit selfheal_metrics? +

Yes. Add a rate_limit block to the selfheal_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.

How do I block selfheal_metrics completely? +

Set action: deny in the PolicyLayer policy for selfheal_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.

What MCP server provides selfheal_metrics? +

selfheal_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.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.