Home/Videos/Voice AI and an MCP server

Video walkthrough · Voice AI and MCP

Controlling a HighLevel Subaccount by Voice With an MCP Server

Four phone calls to a voice agent, and a look at the server and tools that do the work.
The video plays here, loaded from YouTube when you press play.Watch on YouTube

In this video Michael Reimer explains what a model context protocol (MCP) server is and shows one running a GoHighLevel subaccount through HighLevel Voice AI. On live phone calls, the voice agent removes a tag, sends an email, looks up a contact and starts an outbound call. It is for agencies curious about voice control of a CRM.

He starts with a plain description. An MCP server is like a smart helper that keeps the parts of a computer system talking to each other the right way, by sharing information in a format they all understand. His comparison is a coach during a football game. The coach does not play. He tells each player what is happening and what to do next, so the team works together.

What can the voice agent do on a live call?

The test account has a dummy contact named John Doe with a tag called AI Off. Michael dials the agent, which answers as his GoHighLevel assistant and asks how it can help. He says to remove the tag AI Off from contact John Doe. The agent confirms it is done, and after a refresh the tag is gone from the record.

The second call is the one he pictures using on the road. He asks the agent to send an email to John Doe, gives a subject and dictates the message about a meeting at 9:00 the next morning. The agent confirms, and the email is in the inbox, sent through his Gmail.

On the third call he says search contact John Doe. The agent reads back the name, phone, email, address and company name, and mentions that the contact has a couple of open opportunities. You can have it return as much or as little data as you like. That is set in the webhook.

How do the webhook, the AI agent and the MCP client connect?

Michael uses n8n as the medium between the voice agent and the MCP server. A standard webhook comes in from HighLevel. Whenever the voice agent passes along a request, it arrives at that webhook and goes into an AI agent with an extensive prompt.

Three things hang off that AI agent. A chat model works behind the scenes to decide which tools to use. Memory keeps track of the conversation. The MCP client is what reaches out to the tools. When the tools finish, the result comes back, the workflow responds to the webhook, and HighLevel updates the voice agent, which tells you on the phone what happened. In short, the client talks to the server, the server sends the request to individual tools, and the answer travels back the same way.

Four objects in a row joined by arrows and labeled Voice call, Webhook, AI agent and Tools, ending in a toolbox that holds a wrench, a tag and an envelope

Which tools does the MCP server expose?

Michael zooms in on the server workflow, where all the tools sit. On the HighLevel side there are tools to search, create, update and get contacts. Task tools get, create and update tasks. Appointment tools book an appointment with a contact, get a contact's appointments and delete them. Others send an SMS, update conversations, add and remove tags, create, get, delete and move opportunities along the pipeline, and add or remove a contact from a workflow.

He singles out tags, because so much in HighLevel runs on them. Adding or removing one by voice can put a contact into a workflow or stop calls to that contact.

A few tools sit outside HighLevel. One is a maps scraper, which he could ask to collect the electricians in a zip code into a sheet. One is the Gmail tool from the second demo. The last is outbound AI calling. You can connect as many or as few tools as you want.

A hub labeled MCP server connected by ribbons to a tag, an envelope, a calendar, a chat bubble and a phone handset above a plate labeled Tools

How is the voice agent set up inside HighLevel?

Inside the test account the voice agent is an ordinary inbound agent with a basic greeting, the one heard at the start of every demo call. The work happens in Agent Goals. The prompt there covers the greeting, what happens during the call and the flow of the call.

The most important part is a custom action that summarizes the task and sends it to the webhook. Michael notes that custom actions had only recently been added to HighLevel when he recorded this. That one action is the entire link between the phone call and the automation.

Can you start an outbound call by voice?

That is the last demo. Michael calls the agent from his cell phone and says outbound call to contact John Doe. The agent asks him to confirm, then starts it. His phone rings, and a second AI agent opens a sales conversation with him, asks two qualifying questions and offers to set up a call with a strategy team.

The outbound call is prompted dynamically. On one call you could tell it to talk about database reactivation, and on the next you could have it call a different contact about Voice AI.

How do you connect a HighLevel voice agent to an MCP server?

The build, reduced to its parts.

  1. Create the voice agent. Give a HighLevel Voice AI agent a clear greeting and a prompt that describes the call flow.
  2. Add the custom action. In Agent Goals, add a custom action that summarizes the caller's request and sends it to a webhook.
  3. Route the webhook. Send it to an AI agent with a chat model, memory and an MCP client.
  4. Connect the tools. Link the MCP server to tools for contacts, tasks, appointments, SMS, conversations, tags, opportunities and workflows.
  5. Return the result. Send it back through the webhook so the voice agent can confirm the task.
  6. Limit what is read back. Control how much contact data the agent speaks, since that is set in the webhook.

What changes when you can run the CRM by phone?

Tasks that needed a screen become something you say. Removing a tag, sending an email or checking a contact can happen while you are driving between appointments. Michael's phrase for where it can go is that the sky is the limit, because any tool you connect becomes something the agent can do.

He is also clear about the cost. He shares the workflow, the prompts and screenshots so people can import them without much heavy lifting, but he cannot provide unlimited technical support. The follow up video on importing the MCP workflow shows the file itself, and the page on n8n and HighLevel covers the platform in between.

To build the voice agent side in your own account, start a GoHighLevel 30 day trial through Michael's link. Agencies planning to offer this to clients should also read about the Founder Plan.

This article was written from the video transcript. Michael Reimer is a HighLevel Commander and a sponsored affiliate, which means he earns when people sign up through his link.

Questions

MCP server questions.

What is an MCP server, in plain terms?

Michael describes an MCP server as a smart helper that keeps the parts of a computer system talking to each other the right way, by sharing information in a format they all understand. His comparison is a football coach, who does not play but tells each player what is happening and what to do next.

What can the voice agent do in HighLevel?

On live calls in the demo it removes a tag, sends an email, looks up a contact and starts an outbound call. The server also exposes tools for contacts, tasks, appointments, SMS, conversations, tags, opportunities and workflows. Michael says you can connect as many or as few tools as you want.

How does the voice agent pass requests to the server?

Through a custom action in Agent Goals that summarizes the task and sends it to a webhook. The webhook hands the request to an AI agent in n8n, and its MCP client reaches out to the tools. Michael says that one custom action is the entire link between the phone call and the automation.

Which platform connects the voice agent to the MCP server?

Michael uses n8n as the medium between the voice agent and the MCP server. A standard webhook receives the request from the HighLevel voice agent. An AI agent with a chat model and memory decides which tools to use, and an MCP client calls them. The result travels back the same way.

How much contact information does the agent read back?

As much or as little as you like. Michael says that is set in the webhook. In the demo he says search contact John Doe, and the agent reads back the name, phone, email, address and company name, and mentions that the contact has a couple of open opportunities.

Does Michael share the workflow?

Yes. He shares the workflow, the prompts and screenshots so people can import them without much heavy lifting, though he cannot provide unlimited technical support. His follow up video on importing the MCP workflow shows the file itself, including the two parts of the build and the credentials you need to add.

Viewer questions

Questions viewers asked.

Can this MCP server build websites or funnels in HighLevel?

Not in the build Michael shows. The tools on his server cover contacts, tasks, appointments, SMS, conversations, tags, opportunities and workflows, plus three outside tools: a maps scraper, Gmail and outbound AI calling. None of them creates a website or a funnel page. He does say you can connect as many or as few tools as you want, so the list is a starting point, not a limit.

What does it cost to run a HighLevel voice agent with n8n and an MCP server?

Michael gives no total in the video, and the cost has four parts. HighLevel bills Voice AI by the minute, covered by an AI Employee plan or pay per use, and phone charges apply to every call on top. n8n is a separate tool you run and pay for yourself. The chat model behind the agent is billed by its provider. The AI usage costs page covers the HighLevel side.

Which credentials does the MCP voice agent workflow need?

All of them have to be your own. In the follow up video Michael explains that he removed his credentials from the shared file. You set up authorization for each tool you keep and a private integration key for HighLevel, then test by voice. The video on importing the MCP workflow walks through the file and its two parts.

Does GoHighLevel have its own MCP server?

Yes. HighLevel has an official MCP server, also called the LeadConnector MCP server, that assistants such as Claude and ChatGPT connect to with an OAuth sign in and no API key. That is separate from this video, where Michael builds his own server in n8n and reaches it from a voice agent. The guide to Claude with the HighLevel MCP server covers the official one.

Can n8n connect to HighLevel without the custom server in this video?

Yes. The n8n page on this site explains that n8n can connect through the HighLevel MCP connection. You authorize the account and n8n workflows can use HighLevel tools, with each step asking HighLevel for what it needs inside the access you approved. The connection does not copy data. See n8n and HighLevel for both ways to use n8n.

Does the voice agent confirm before it places an outbound call?

Yes, in the demo. Michael says outbound call to contact John Doe, and the agent asks him to confirm before it starts the call. His phone then rings and a second AI agent opens the conversation. The outbound call is prompted dynamically, so one call can be about database reactivation and the next can go to a different contact about Voice AI.

Next step

See it in your own account. Thirty days, every feature.

Start a 30 day trial through Michael's link, build the first system and test it before the first invoice. Usage fees for phone, SMS, email and AI can apply during the trial.

HighLevel has three plans at a flat monthly price, each with unlimited users and contacts. See what each one includes and what it costs.

Compare the PlansStarter, Unlimited and Founder
⌃

Site preview

Explore the next page

This destination is reserved in the page inventory and is not built yet.