coordination_topology · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What coordination_topology does on Claude Flow

AI agents use coordination_topology to create or update resources in Claude Flow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Flow environment.

WHY IT NEEDS A POLICY

Why coordination_topology needs a policy

This tool modifies the configuration of multi-agent swarm topology and coordination parameters. While it does not delete data (Destructive), execute arbitrary code (Execute), or move money (Financial), it creates or modifies the coordination structure that governs how distributed agents operate. The blast radius is high because misconfiguration could disrupt enterprise workflows across multiple agents.

From the tool's definition Tool description states 'Configure swarm topology' and 'use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

coordination_topology Rate-limited

coordination_topology stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "coordination_topology": {
      "limits": [
        {
          "counter": "coordination_topology_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Flow, so you can run agents against it safely.

FAQ

Questions about coordination_topology

What does the coordination_topology tool do? +

Configure swarm topology Use when native Task is wrong because the work crosses multiple agents that need to vote/sync/load-balance — TodoWrite + a single Task cannot orchestrate consensus. For one-off subtask dispatch, native Task is fine. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on coordination_topology? +

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

coordination_topology is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit coordination_topology? +

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

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

coordination_topology 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.