MiiTel Alternative MCP. Log records, manage exports, centralize voice intel.

You’re done jumping between dashboards or manually exporting files. This server lets your AI agent talk directly to MiiTel's backend, handling all the heavy lifting for logging and data management through simple natural language prompts. It keeps you from having to mess with webhooks or complicated APIs yourself; you just tell your agent what you need.

For getting external call logs into MiiTel, you’ll use the create_call_record tool. You feed this function the raw data from an outside phone system—that's simulating a webhook event—and the server imports it directly into your MiiTel account. It treats that incoming information like a real, native call log entry. This means if you got a third-party CRM or another platform logging interactions, you just pipe that data through create_call_record, and it shows up in your system without any manual cleanup or mapping.

When you need to import meeting details from outside systems, you'll use the create_meeting_record tool. This is different from call logging because this function handles more metadata; it imports not just the basic transcript data, but also specific participant information and host details. Like the call logger, it simulates an incoming webhook event, which is how it gets all that structured data into MiiTel’s records seamlessly.

You use create_meeting_record when you've got a batch of meeting transcripts or summaries from another service, and you want them treated as official parts of your MiiTel history.

If the problem isn't logging new events, but rather getting historical data out, you’ll need to trigger an export queue. You start that process with create_queue. Telling the server to use this tool kicks off a background job—a data queue—that starts generating a CSV file containing all the call history or meeting records you specify.

This isn't instant; it runs in the background, and its whole point is to gather potentially massive amounts of historical data into one exportable format. You tell it what kind of data you want (calls or meetings), and it initiates the gathering process.

Once that job is queued up, you need to know what's going on. That’s where list_queues comes in. This tool lets you check the status of every single export job—past jobs and current ones, too. It gives you a clear breakdown: Is it still WAITING for processing? Is it currently PROCESSING and taking its sweet time? Or did it finish up cleanly and is marked as COMPLETED? If something goes wrong, this tool tells you immediately if the job hit an ERROR, so you know exactly where to look.

You use list_queues anytime you need visibility into your data export pipeline.

Basically, you're handling a full lifecycle: logging new calls with create_call_record, logging complete meetings with create_meeting_record, kicking off the historical extraction using create_queue, and finally monitoring the whole deal with list_queues. It keeps your entire voice intelligence data management system in one spot, letting you manage everything through simple prompts to your agent.