How to Use the MiiTel MCP in AutoGen

Q: How do AutoGen agents use MiiTel Alternative to ingest calls?

You register the tools with the AssistantAgent using the MCP adapter. The agent calls createcallrecord when the group consensus requires a new call log.

Q: Can AutoGen agents manage export queues via MiiTel Alternative?

Yes, the coordinator agent can call createqueue to start an export. Another agent can use listqueues to verify when the CSV is ready.

Let AutoGen agents debate and coordinate call record ingestion and queue creation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect MiiTel MCP to AutoGen

Create your Vinkius account to connect MiiTel to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup MiiTel with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Coordinate call records across AutoGen agents

`create_call_record` lets your AutoGen support agent register call webhooks after a debate with your quality control agent. The agents negotiate whether the call meets quality standards before writing the record. This collaborative check prevents messy or incomplete call data from entering your database. Your agents handle the validation logic entirely through conversation.

Manage CSV queues with AutoGen MCP Server tools

`create_queue` allows your data analyst agent to request a new CSV export when the budget agent approves the API cost. The agents communicate to ensure exports only run when necessary. Once approved, the analyst agent triggers the queue creation. This keeps your API usage efficient and prevents runaway export costs.

Track export queues through agent consensus

`list_queues` gives your monitoring agent the ability to check active CSV export tasks. The agent reports the status back to the coordinator agent to schedule the next processing step. If a queue fails, the agents discuss the error and decide whether to retry. This automated troubleshooting keeps your voice data pipeline running without human intervention.

Setup guide

Set up MiiTel MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes MiiTel tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="MiiTel_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent MiiTel data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="MiiTel_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent MiiTel data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by MiiTel. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect MiiTel now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about MiiTel MCP in AutoGen

You register the tools with the `AssistantAgent` using the MCP adapter. The agent calls `create_call_record` when the group consensus requires a new call log.

Yes, the coordinator agent can call `create_queue` to start an export. Another agent can use `list_queues` to verify when the CSV is ready.

The server supports both stdio and Streamable HTTP transports. You configure it in AutoGen using `StreamableHttpServerParams` to connect your agents.

Yes, you can pass different tool lists to different agents. For instance, give `create_meeting_record` to your recorder agent and `list_queues` to your analyst agent.

The server processes your call and meeting record metadata in a zero-trust sandbox. No queue lists or webhook payloads are cached or stored on external disks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript