federation_send · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What federation_send does on Claude Flow

AI agents invoke federation_send to trigger actions in Claude Flow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why federation_send needs a policy

This tool triggers external operations by sending messages to federated peers through a pipeline, constituting an Execute action. It has financial implications via token/USD spend caps across hop chains, but these appear to be guardrails rather than the primary action (money movement).

From the tool's definition 'Send a message to a federated peer through the PII pipeline and security gates' with 'budget controls... maxTokens/maxUsd cap cumulative spend across the hop chain'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

federation_send Rate-limited

federation_send stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "federation_send": {
      "limits": [
        {
          "counter": "federation_send_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 federation_send

What does the federation_send tool do? +

Send a message to a federated peer through the PII pipeline and security gates. Optional budget controls (ADR-097): maxHops defaults to 8 to prevent recursive delegation; maxTokens/maxUsd cap cumulative spend across the hop chain. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on federation_send? +

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

federation_send is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit federation_send? +

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

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

federation_send 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.