How to Use the Vapi MCP in LangChain

Q: How does Vapi integrate with LangChain for multi-step actions?

Vapi exposes its tools, like createphonecall, as discrete nodes in your chain. Your agent decides which tool to call and what the input needs to be based on intermediate results.

Q: Can I list all available Vapi assistants using LangChain?

Yeah, you can use listassistants. This gives your agent a full roster of every Voice AI assistant persona currently configured within Vapi for reference or updating.

Q: What details does the MCP Server provide about call outcomes using LangChain?

The getcalldetails tool returns transcripts and metrics, which are ideal inputs. Your agent can process this raw data immediately to make a decision or generate a follow-up action.

Build complex, observable AI pipelines with Vapi and LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vapi MCP to LangChain

Create your Vinkius account to connect Vapi 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 Vapi with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Outbound Voice Calls

You can start a call using `create_phone_call`, giving your agent the required phone number ID and customer details. This lets you model complex, multi-step reasoning where one step is calling someone and another step is analyzing the result. After the conversation wraps up, you grab all the data with `get_call_details`. This tool returns everything—transcripts, metrics, and call status—so your agent can feed it into the next node of the chain.

Configure Assistant Personas

Need a new AI persona? Use `create_assistant` to set up the core voice, model, and transcriber for your assistant. You'll get a JSON string back with all the necessary configuration details. If you need to tweak that persona later on, just hit `update_assistant`. This lets your agent adjust its own behavior without having to rebuild the whole setup.

Track and List Resources

Your workflow needs visibility. Use `list_calls` to see a rundown of recent or active voice calls managed by Vapi. It's good for debugging those multi-step processes. For infrastructure setup, you can check out all available numbers with `list_phone_numbers`, making sure your agent has access to the right endpoints.

Setup guide

Set up Vapi 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 Vapi 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({
    "vapi-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 Vapi 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 Vapi. 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 Vapi 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 Vapi MCP in LangChain

Vapi exposes its tools, like `create_phone_call`, as discrete nodes in your chain. Your agent decides which tool to call and what the input needs to be based on intermediate results.

Yeah, you can use `list_assistants`. This gives your agent a full roster of every Voice AI assistant persona currently configured within Vapi for reference or updating.

The `get_call_details` tool returns transcripts and metrics, which are ideal inputs. Your agent can process this raw data immediately to make a decision or generate a follow-up action.

Absolutely. Since your pipelines are built on tool outputs becoming next inputs, Vapi's structured tools fit perfectly into the ReAct agent pattern you're building.

The server handles call metrics and transcripts. These are the raw conversational and performance records that your agent can access and process.

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