escalate · Interagent MCP: Risk & Policy

WHAT IT DOES

What escalate does on Interagent

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

WHY IT NEEDS A POLICY

Why escalate needs a policy

The tool writes a status/flag to a message (marking it as blocked) and sends a notification to the original sender. This is a reversible state change and notification action — no data is deleted, no code is executed, and no financial transaction occurs. The severity is medium because misuse could disrupt agent coordination workflows and generate false escalations that waste human attention.

From the tool's definition Flag a message as blocked. Notifies the sender that human attention is needed at your instance.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

escalate Rate-limited

escalate 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": {
    "escalate": {
      "limits": [
        {
          "counter": "escalate_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 Interagent, so you can run agents against it safely.

FAQ

Questions about escalate

What does the escalate tool do? +

Flag a message as blocked. Notifies the sender that human attention is needed at your instance. It is categorised as a Write tool in the Interagent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on escalate? +

Register the Interagent MCP server in PolicyLayer and add a rule for escalate: 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 Interagent. Nothing to install.

What risk level is escalate? +

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

Can I rate-limit escalate? +

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

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

escalate is provided by the Interagent MCP server (signalclaude/interagent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.