How to Use the Vibrato MCP in LangChain

Q: If I use a template with Vibrato and LangChain, what happens?

You'll invoke createcallfromtemplate. The resulting call is initiated using pre-defined negotiation logic. This saves your agent from having to write complex scripting for every common scenario.

Q: Can I see all available templates in LangChain?

Yeah, just hit the listtemplates tool. It gives you a clean list of what negotiation flows are ready to be used by your agent right now. This is how you scope down the possibilities.

Build multi-step phone call workflows with LangChain and the Vibrato MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vibrato MCP to LangChain

Create your Vinkius account to connect Vibrato 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 Vibrato with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Initiate calls using complex prompts

Need to kick off a conversation? You can execute an AI-powered call immediately by passing a prompt, phone number, and locale to `create_call`. The output of this tool provides the initial call ID. Then, you'll pass that resulting ID into another step in your chain, maybe using it to check its status via `get_call_status`, making sure the conversation actually started.

Run calls from defined templates

Don't build the script every time. Start with a pre-written flow by calling `create_call_from_template`. This handles complex call negotiation using established patterns, and you can first review all available options using `list_templates`. This allows your agent to pick the right playbook before execution, giving it reliable context that other communication methods lack.

Monitor and list all active calls

To track what's happening behind the scenes, you can use `list_calls` to get a full manifest of every AI call. Checking the status is simple with `get_call_status`, giving you immediate feedback on whether the conversation completed or stalled. This visibility means your agent never runs blind; it always knows the current state of its communication payload, which is key for reliable multi-step logic.

Setup guide

Set up Vibrato 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 Vibrato 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({
    "vibrato-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 Vibrato 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 Vibrato. 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 Vibrato 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 Vibrato MCP in LangChain

The MCP Server lets you treat every tool output as the input for the next step. For example, running `list_calls` gives a list of IDs, and your agent immediately uses one of those IDs to call `get_call_status`. It keeps the entire process grounded in real data.

The server handles communication metadata, specifically things like phone numbers, locales, and the current call status. Your agent uses this information to decide its next logical step in the pipeline.

You'll invoke `create_call_from_template`. The resulting call is initiated using pre-defined negotiation logic. This saves your agent from having to write complex scripting for every common scenario.

Yeah, just hit the `list_templates` tool. It gives you a clean list of what negotiation flows are ready to be used by your agent right now. This is how you scope down the possibilities.

The server touches communication metadata, including phone numbers and call status records. Data is managed securely through Vinkius's zero-trust architecture, ensuring your tokens handle access.

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