AI agents use update_call to create or update resources in Retellai — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Retellai environment.
Updating a call modifies state but does not delete or destroy data (ruling out Destructive) and does not execute arbitrary code or financial transactions. This is a reversible Write operation on call metadata/state. Severity is medium because misuse could affect call routing, configuration, or duration, potentially impacting business operations or user experience.
From the tool's definition Tool name 'update_call' with description 'Updates an existing call' indicates modification of call state. Server context shows call management operations (create_phone_call, delete_call, update_call).
Attacks that exploit this kind of access
Updates an existing call. It is categorised as a Write tool in the Retellai MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Retellai MCP server in PolicyLayer and add a rule for update_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.
update_call is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_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 update_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.
update_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 →