agent_health

SERVERClaude Flow SOURCEclaude-flow

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-ruvnet-claude-flow/agent-health.md

WHAT IT DOES

What agent_health does on Claude Flow

AI agents call agent_health to retrieve information from Claude Flow without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why agent_health is rated Low

Retrieves historical metrics and health status data with no side effects or modifications.

From the tool's definition Report measured outcomes, API success-ratio health, error rate, response-latency. Does not measure task correctness.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs agent_health safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agent_health, this is the rule to start with:

agent_health Allowed

agent_health is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "agent_health": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Claude Flow, apply this rule, and every agent_health call is checked against it from then on.

FAQ

Questions about agent_health

What does the agent_health tool do? +

Report measured agent_execute provider-call outcomes over the last 20 calls: API success-ratio health (0-1), error rate, and response-latency p50/p95. This does not measure task correctness. Agents with no observed calls have unknown health; registration is not proof of a running process. Native Task and hooks_post-task outcomes are not recorded here. Use when you need measured reliability for agents driven through agent_execute; native Task results are invisible to this tool, so inspect those directly. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on agent_health? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for agent_health: 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 Claude Flow. Nothing to install.

What risk level is agent_health? +

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

Can I rate-limit agent_health? +

Yes. Add a rate_limit block to the agent_health 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 agent_health completely? +

Set action: deny in the PolicyLayer policy for agent_health. 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 agent_health? +

agent_health is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Claude Flow, and thousands of servers like it.

This server

All 546 Claude Flow tools →

Across the catalogue

comfy_agent_compute on Comfy → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →