agent_list

List every Ruflo-tracked agent in the registry with its type, model, status, and taskCount. Use when native Task tool is wrong because you need to see the swarm-wide agent inventory across turns (which agents exist, their roles, their cost-tracking handles) rather than spawn a new one-shot Task. ...

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

What agent_list does on Claude Flow

AI agents call agent_list 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 agent_list needs a policy

This is a pure information retrieval tool that queries agent registry state without creating, modifying, deleting, or executing any operations. The optional filtering parameters (status/domain/agentType) are read-only query constraints, not write operations. The severity is low because listing agent metadata poses minimal risk—it does not spawn agents, terminate them, or affect system state.

From the tool's definition Tool description states 'List every Ruflo-tracked agent in the registry' and 'see the swarm-wide agent inventory'. The verb 'List' combined with 'use when you need to see' indicates data retrieval with no modification or side effects.

Risk signalsBulk/mass operation — affects multiple targets

Questions about agent_list

What does the agent_list tool do? +

List every Ruflo-tracked agent in the registry with its type, model, status, and taskCount. Use when native Task tool is wrong because you need to see the swarm-wide agent inventory across turns (which agents exist, their roles, their cost-tracking handles) rather than spawn a new one-shot Task. Filter by status/domain/agentType if needed. For starting a fresh single-shot subagent, native Task is fine. 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_list? +

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

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

Can I rate-limit agent_list? +

Yes. Add a rate_limit block to the agent_list 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_list completely? +

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

agent_list 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.