How to Use the Mio MCP in LangChain

Q: How do I handle running out of call credits during an agent run?

You should configure your agent to call getcreditbalance at the start of a chain. If the balance falls below a specific threshold, your agent can halt execution before attempting to invoke startaicall.

Chain Mio voice calls and live transcripts directly into your LangChain multi-step reasoning agents without writing glue code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mio MCP to LangChain

Create your Vinkius account to connect Mio 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 Mio with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step voice agents with LangChain and the Mio MCP Server.

LangChain agents can string together Mio voice tasks sequentially. Your agent can run `list_calls` to find an ongoing conversation, grab the text via `get_call_transcript`, and immediately feed that text into a downstream LangChain LLM chain to draft a follow-up email. You don't have to manually pass variables between Mio API requests inside LangChain. The framework handles the state transition, letting your agent evaluate the output of `get_call_summary` before deciding if it needs to trigger `terminate_call` or fire off a new notification via `create_webhook`.

Track Mio latency and tool execution with LangSmith.

Debugging Mio voice calls gets messy fast. When you connect this server to LangChain, every execution of `start_ai_call` or `get_call_details` is logged automatically in your LangSmith dashboard. This visibility keeps your production LangChain runs predictable. If a Mio call fails or a transcript from `get_call_transcript` returns empty, you can inspect the raw JSON payload in your LangSmith trace to fix the issue.

Combine Mio voice tools with LangChain integrations.

LangChain lets you mix these Mio voice tools with its ecosystem of over 500 integrations. Your agent can pull user records from a database, check your remaining Mio funds with `get_credit_balance`, and choose a custom voice via `list_available_voices` based on the user's profile. This makes your LangChain applications vastly more capable. Instead of running Mio voice features in a silo, you can write a single chain where your agent checks customer history, starts a call, and deletes obsolete notification endpoints using `delete_webhook` all in one go.

Setup guide

Set up Mio 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 Mio 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({
    "mio-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 Mio 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 Mio. 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 Mio 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 Mio MCP in LangChain

You initialize the client using the LangChain MCP adapter and pass the tools directly to your agent executor. The agent can then use tools like `get_call_transcript` and feed the resulting text straight into the next step of your chain.

Yes. Since the server runs as a standard toolset within the LangChain framework, every call to `start_ai_call` or `list_calls` is automatically tracked in LangSmith. You can monitor latency, token usage, and payload structures in real time.

You can let your LangChain agent manage its own event listeners dynamically. The agent calls `create_webhook` to register an endpoint and uses `list_webhooks` to verify the active configuration during its execution run.

You should configure your agent to call `get_credit_balance` at the start of a chain. If the balance falls below a specific threshold, your agent can halt execution before attempting to invoke `start_ai_call`.

All data transit occurs within a secure, ephemeral V8 isolate container that destroys itself after execution. Your sensitive voice calls, written transcripts, and webhook URLs are never stored or logged on our infrastructure, keeping your communications private.

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