retell_end_chat · Retell AI MCP Server MCP: Risk & Policy

WHAT IT DOES

What retell_end_chat does on Retell AI MCP Server

AI agents invoke retell_end_chat to trigger actions in Retell AI MCP Server. 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 retell_end_chat needs a policy

Terminating an active chat session is an external operation that triggers a state change in the platform (ending a live session). It is not a simple data read or write, but an action that affects an ongoing operation. While not irreversible in a data-destruction sense, it cannot be undone once the session is terminated, making it closer to Execute than Write.

From the tool's definition End an active chat session

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

retell_end_chat Rate-limited

retell_end_chat 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": {
    "retell_end_chat": {
      "limits": [
        {
          "counter": "retell_end_chat_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 Retell AI MCP Server, so you can run agents against it safely.

FAQ

Questions about retell_end_chat

What does the retell_end_chat tool do? +

End an active chat session. It is categorised as a Execute tool in the Retell AI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on retell_end_chat? +

Register the Retell AI MCP Server MCP server in PolicyLayer and add a rule for retell_end_chat: 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 Retell AI MCP Server. Nothing to install.

What risk level is retell_end_chat? +

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

Can I rate-limit retell_end_chat? +

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

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

retell_end_chat is provided by the Retell AI MCP Server MCP server (itsanamune/retellsimp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.