AI agents invoke create_phone_call to trigger actions in Retellai. 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.
Creating a phone call triggers an external operation (an actual phone call) whose effects depend on arguments like the destination number and agent. This is not merely writing data to a database — it initiates real-world communication. It could be misused to call arbitrary numbers, potentially incurring costs or harassment.
From the tool's definition "Creates a new phone call" - initiates an outbound phone call, triggering an external real-world telephony operation
Attacks that exploit this kind of access
Creates a new phone call. It is categorised as a Execute tool in the Retellai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Retellai MCP server in PolicyLayer and add a rule for create_phone_call: 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 Retellai. Nothing to install.
create_phone_call is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the create_phone_call 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.
Set action: deny in the PolicyLayer policy for create_phone_call. 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.
create_phone_call is provided by the Retellai MCP server (@abhaybabbar/retellai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →