### Answer Happy to help with your integration question! Retell AI offers several integration options: Custom Functions – Extend your agent's capabilities by integrating external APIs. When called, Retell sends a POST request to your specified URL with the function name and parameters. [(1) ]() Webhooks – Get notified of call events (call_started, call_ended, call_analyzed) via POST requests to your endpoint. [(2) ]() Native Integrations – Retell has built-in integrations with Make and Zapier. [(3) ]() Custom LLM Integration – Connect your own LLM via WebSocket if you have specific requirements. [(4) ]() *MCP (Model Context Protocol) * – Connect your own MCPs to invoke tools, call HTTP-based services like Zapier or custom APIs, and trigger workflows. [(3) ]() What specific integration are you looking to set up? I can provide more detailed guidance once I know what you're trying to accomplish.

​ To learn more, see the sources I considered: [[1] Integrate any system with custom function](https://docs.retellai.com/build/single-multi-prompt/custom-function) [[2] Webhook Overview](https://docs.retellai.com/features/webhook-overview) [[3] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[4] Integrate Function Calling](https://docs.retellai.com/integrate-llm/integrate-function-calling) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

### Answer I don't have specific documentation about "Open Claw" or "Clawbot" in the available sources. However, Retell AI does support integrating voice agents with external systems, which could potentially work for your use case. Here are the integration approaches you could use: Custom Functions – You can create a custom function that makes HTTP requests (GET, POST, PUT, PATCH, DELETE) to external APIs when triggered during a call. [(1) ]() This would allow your voice agent to send commands to any system that exposes an API. *MCP (Model Context Protocol) * – Retell's MCP Node lets your voice agents call any HTTP-based service, trigger workflows, and fetch live data in real time. Custom LLM Integration – If you need more control, you can set up a WebSocket server that connects your own backend to Retell, allowing you to process commands and integrate with external systems. [(2) ]() [(3) ]() If Open Claw/Clawbot has an API endpoint, you could configure a custom function to send commands to it based on voice input. The agent would call the function, which would then make the appropriate HTTP request to your robot's API. Could you share more details about what API or interface Open Claw uses? That would help me give more specific guidance on the best integration approach.

​ To learn more, see the sources I considered: [[1] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[2] Setup WebSocket Server](https://docs.retellai.com/integrate-llm/setup-websocket-server) [[3] Custom LLM Overview](https://docs.retellai.com/integrate-llm/overview) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.