swarm_monitor

Monitor swarm activity (V2 compatible). Deprecated: Use swarm/status with includeMetrics instead.

Server Claude Flow claude-flow
Category Read
Risk class Low
Parameters 00 required

What swarm_monitor does on Claude Flow

AI agents call swarm_monitor 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.

Why swarm_monitor needs a policy

This tool retrieves and observes swarm metrics and activity data without modifying, executing code, or triggering side effects. Monitoring is inherently a read operation. Even in a swarm orchestration context, passive health/status observation poses minimal risk compared to spawn/terminate/update operations on the same server.

From the tool's definition Tool name 'swarm_monitor' and description 'Monitor swarm activity' indicates passive observation/querying of metrics and status. The directive to use 'swarm/status' as a replacement suggests read-only telemetry.

Questions about swarm_monitor

What does the swarm_monitor tool do? +

Monitor swarm activity (V2 compatible). Deprecated: Use swarm/status with includeMetrics instead. 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 swarm_monitor? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for swarm_monitor: 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 swarm_monitor? +

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

Can I rate-limit swarm_monitor? +

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

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

swarm_monitor 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.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.