We use MCP in production for our customer facing voice agents. Our custom MCP server defines tools and resources that the voice agents need access to to interact with our customers. (E.g. scheduling appointments, checking order status, etc).
Now we can point any voice agent platform we choose -- eleven labs, vapi, pipecat, whatever -- at our custom MCP server and it instantly has an understanding of the tools available, their inputs, and how to use them.
Compared to the alternatives everyone on HN champions, like clis and APIs, this is a no brainer. I'm honestly not even sure what the realistic alternative would even be.
Am I supposed to package and distribute a cli to ElevenLabs and ask them to use it? Give them a full API spec to implement for me?
I give them an endpoint and credentials and their platform instantly knows how to talk to mine. No one at ElevenLabs knows or cares about our implementation details.
HN has trouble seeing past the "developer in a terminal coding with Claude Code" use case for using AI. Real production agents have use cases that are very different!
When you don't own every piece of an integration with another system, there needs to be a well defined standard. That's what MCP provides.
Excuse me for being dense but I'd love to know more, if you can share. So you offer a voice agent for checking appointments and orders and stuff, is that through your app or website or something? So you make a button in your app which says "talk to our AI", and you've got the button set up so that it can send the customer's input query, along with a bit of text saying "our MCP is here, use it to answer the query", to any one of the voice agent providers? then you get some audio data in return that you play to the user?
We use a Twilio integration to make it work over a real phone line, but it could just as well be an app or websocket connection in a browser.
Voice transport medium aside, the actual use case is not quite what you described.
Companies like Eleven Labs and Vapi provide a full end to end voice agent platform. They handle the STT -> LLM -> TTS pipeline and infrastructure for voice agents. Think of a customer talking to a virtual receptionist to schedule an appointment.
On the ElevenLabs platform, you provide them a system prompt (or an entire workflow/graph of system prompts) that instruct the voice agent on how to talk to the customer, tone, guardrails, how to answer specific questions, etc.
At some point we need that LLM agent, running on an infrastructure we don't control, to talk to our "CRM" (for simplicity sake). Enter MCP.
The MCP server we build and host supplies the "tools", like list_appointments, schedule_appointment, cancel_appointment-- whatever they may be.
When eleven Labs voice agent connects, it sees all the tools available and can use them per the instructions in the system prompt.
How is security handled in a situation like this? (I'll end up reading up on it). But I mean things like how does the API let a specific session with a specific user only surface information for that specific user from the available tooling?
You first authenticate via the phone (you can run an initial api call on phone start,) save session credentials in state on 11labs side and can then pass them back to future tool calls. You can then authenticate via a passcode if you wish
5.6 class models have a brand new caching architecture. Make sure you were using the prompt cache breakpoints and cache keys correctly - it's much different than < 5.5 and makes a huge difference for many production workloads.
Yeah, that would be a problem. Luckily, the actual post we're discussing isn't putting any advertising in the model.
This is a very important distinction to make -- complaints should be be about what is happening, and should distinguish that from what is not yet happening and should not. Because beyond the maxim that we should try to deal in facts... if OpenAI thinks people can't tell the difference anyways, they'll be justified in thinking they may as well just do the thing they're already being accused of doing.
Why would you think that? An ad supported product has misaligned incentives, everyone can see that and that's why the confidence erodes from that moment on.
You're living in the era in which saying "Stallman was right" is a dead cold take. Every big tech company sold out exactly like the hippies told you they would back when Google was a dream place to work for and Meta was still a twinkle in zuk's eyes.
Now, well, if you do the same exact search, at least in my location (and with UBlock disabled) it's frankly a mess but must admit that sponsored links are not even the first thing you see. There is the AI result, then the Wikipedia result, then some random result, then the sponsored block with a flat headline separating it and then the organic results, I presume.
Something similar has been happening to me with Ghostty, but there is no error message or link and it only happens when Claude uses it's interactive questions interface.
It becomes completely unresponsive to any input except scrolling. I can't select options or even cancel out.
Now we can point any voice agent platform we choose -- eleven labs, vapi, pipecat, whatever -- at our custom MCP server and it instantly has an understanding of the tools available, their inputs, and how to use them.
Compared to the alternatives everyone on HN champions, like clis and APIs, this is a no brainer. I'm honestly not even sure what the realistic alternative would even be.
Am I supposed to package and distribute a cli to ElevenLabs and ask them to use it? Give them a full API spec to implement for me?
I give them an endpoint and credentials and their platform instantly knows how to talk to mine. No one at ElevenLabs knows or cares about our implementation details.
HN has trouble seeing past the "developer in a terminal coding with Claude Code" use case for using AI. Real production agents have use cases that are very different!
When you don't own every piece of an integration with another system, there needs to be a well defined standard. That's what MCP provides.
reply