Perform system health check Use when native Bash is wrong because you need Ruflo runtime metrics (HNSW index size, ReasoningBank state, swarm health, breaker status) — those are not in /proc, only in the running daemon. For OS-level info (uptime, disk, mem), native Bash + standard tools are fine.
AI agents call system_health to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and reports on system state and daemon metrics without modifying any data, executing code, or triggering external operations. It is purely informational—a diagnostic read operation similar to status queries. While it accesses internal daemon state rather than standard OS calls, the core function remains read-only retrieval of telemetry data.
From the tool's definition Tool description states it performs a 'system health check' and retrieves runtime metrics (HNSW index size, ReasoningBank state, swarm health, breaker status).
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Perform system health check Use when native Bash is wrong because you need Ruflo runtime metrics (HNSW index size, ReasoningBank state, swarm health, breaker status) — those are not in /proc, only in the running daemon. For OS-level info (uptime, disk, mem), native Bash + standard tools are fine. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for system_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.
system_health 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 system_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.
Set action: deny in the PolicyLayer policy for system_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.
system_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.