AI agents use create_retell_llm 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.
This tool creates a new LLM configuration within the Retell system. Creation operations are Write-category actions that establish new entities. Severity is medium because: (1) it does not directly execute arbitrary code or perform irreversible deletion, (2) the blast radius is limited to LLM configuration objects, and (3) unauthorized LLM creation could enable phishing or social engineering through fake…
From the tool's definition Tool name 'create_retell_llm' and description 'Creates a new Retell LLM' indicate creation of a new resource that modifies system state reversibly.
Attacks that exploit this kind of access
Creates a new Retell LLM. 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 create_retell_llm: 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_retell_llm 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 create_retell_llm 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_retell_llm. 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_retell_llm 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 →