ADR-097 Phase 4: per-peer circuit-breaker state snapshot. Returns each known peer with its lifecycle state (ACTIVE/SUSPENDED/EVICTED), when it changed, and why. Combine with federation_evict / federation_reactivate to operate the breaker manually.
AI agents call federation_breaker_status 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 is a Read operation: it queries and returns circuit-breaker state data with no side effects. The mention of 'Combine with federation_evict / federation_reactivate to operate the breaker manually' confirms those are separate tools; this tool itself only retrieves state.
From the tool's definition Tool returns state snapshots of circuit-breaker status for each peer—'per-peer circuit-breaker state snapshot' listing lifecycle state, timing, and reasons. It is read-only: 'Returns' indicates retrieval without modification.
Attacks that exploit this kind of access
ADR-097 Phase 4: per-peer circuit-breaker state snapshot. Returns each known peer with its lifecycle state (ACTIVE/SUSPENDED/EVICTED), when it changed, and why. Combine with federation_evict / federation_reactivate to operate the breaker manually. 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 federation_breaker_status: 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.
federation_breaker_status 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 federation_breaker_status 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 federation_breaker_status. 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.
federation_breaker_status 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.