retell_create_chat_completion · Retell AI MCP Server MCP

WHAT IT DOES

What retell_create_chat_completion does on Retell AI MCP Server

AI agents invoke retell_create_chat_completion 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_create_chat_completion needs a policy

This tool sends a message to an existing chat session and invokes the agent to produce a response. It triggers an external operation (AI agent execution) rather than merely reading data or creating/modifying stored records. The blast radius is moderate: misuse could cause an agent to say unintended things in active chats, but it doesn't delete data or move money.

From the tool's definition "Send a message in an existing chat session and get the agent" — triggers an external AI agent operation within an active session

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

retell_create_chat_completion Rate-limited

retell_create_chat_completion 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_create_chat_completion": {
      "limits": [
        {
          "counter": "retell_create_chat_completion_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_create_chat_completion

What does the retell_create_chat_completion tool do? +

Send a message in an existing chat session and get the agent. 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_create_chat_completion? +

Register the Retell AI MCP Server MCP server in PolicyLayer and add a rule for retell_create_chat_completion: 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_create_chat_completion? +

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

Can I rate-limit retell_create_chat_completion? +

Yes. Add a rate_limit block to the retell_create_chat_completion 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_create_chat_completion completely? +

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

retell_create_chat_completion 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.