How to Use the MiiTel MCP in LangChain

Q: How do I connect the MiiTel MCP Server to LangChain?

Install langchain-mcp-adapters and use the MultiServerMCPClient to connect to the Vinkius endpoint. From there, call client.gettools() and pass them directly to your agent runner.

Q: Can a LangChain agent analyze MiiTel call sentiment?

Yes, the agent can use getcalldetails to retrieve call quality metrics and sentiment scores. It then processes this data through your LLM chain to generate coaching summaries.

Run multi-step sales coaching chains in LangChain using direct call transcript analysis and performance metrics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MiiTel MCP to LangChain

Create your Vinkius account to connect MiiTel to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup MiiTel with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace call quality across LangChain pipelines

Stop guessing how your reps talk to leads. This MCP Server lets your agent pull raw call data using `list_calls` and inspect individual transcripts with `get_call_details`. You feed this straight into your chain to score tone, objections, and talk-to-listen ratios without writing custom API wrappers. Because it plugs into your existing LangChain setup, you get full visibility through LangSmith. You can track exactly how much context your agent uses when analyzing a customer call, making it easy to debug slow runs or weird outputs.

Sync CRM contacts to clean up conversational context

Your agent needs real names and numbers, not raw IDs. Use `list_synced_contacts` to pull clean CRM data and match it with call records. This keeps your LangChain agents grounded so they do not hallucinate who spoke to whom during last week's demo. You can pass these contacts directly to `list_miitel_users` to see which internal rep handled the account. It turns messy, disconnected call logs into structured data your chains can actually use for automated coaching reports.

Automate meeting analysis chains

Sales reps spend hours writing follow-up emails after video calls. Let your LangChain agent pull meeting records with `list_online_meetings` and dive into the specifics with `get_meeting_details`. The agent takes the meeting notes, drafts a personalized follow-up, and matches it with the customer's history. No manual copy-pasting, just clean data flowing through your chains.

Setup guide

Set up MiiTel MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes MiiTel tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "miitel-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent MiiTel transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters` and use the `MultiServerMCPClient` to connect to the Vinkius endpoint. From there, call `client.get_tools()` and pass them directly to your agent runner.

Yes, the agent can use `get_call_details` to retrieve call quality metrics and sentiment scores. It then processes this data through your LLM chain to generate coaching summaries.

LangChain handles this through standard runnable retry configurations or custom callback handlers. When tools like `list_calls` hit limits, the framework backs off and retries automatically.

Yes. Since it exposes standard tools, you can pair the MiiTel MCP Server with vector databases or email APIs in the same LangChain agent.

Your call logs and CRM contact data never leave your secure LangChain runtime environment. Vinkius runs this MCP Server in an isolated sandbox, meaning your raw voice records and customer phone numbers remain strictly confidential.

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