How to Use the Mav MCP in LangChain

Q: How do I connect the Mav MCP Server to my LangChain agents?

Install langchain-mcp-adapters and initialize the MultiServerMCPClient with your Vinkius endpoint. Retrieve the tools using client.gettools() and pass them directly to your agent constructor to start triggering SMS playbooks.

Run multi-step LangChain pipelines that trigger SMS playbooks and track every conversation state inside LangSmith.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mav MCP to LangChain

Create your Vinkius account to connect Mav 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 Mav with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain SMS playbook triggers with LangChain agents

The Mav MCP server exposes your SMS lead qualification playbooks directly to your LangChain execution graph. By connecting this server, your agent evaluates incoming lead responses and decides when to trigger specific playbooks based on user intent. You pass these capabilities into `create_agent` using the `langchain-mcp-adapters` package. The agent runs asynchronous chains, passing lead details from your database straight into the SMS pipeline to start immediate, automated follow-ups.

Trace SMS conversation states using LangSmith

This MCP Server integrates with your LangChain tracing setup to expose latency, token usage, and payload details for every automated SMS interaction. You see exactly why an agent chose a specific qualification playbook during a live run. Debugging stuck leads becomes straightforward because LangSmith logs the exact inputs sent to the Mav playbooks. You monitor performance metrics without guessing which step in your conversational graph caused a delay.

Build multi-step qualification pipelines

The Mav MCP connection lets you construct complex, conditional routing paths where SMS playbooks feed back into your other LangChain tools. For example, when a lead qualifies via SMS, the agent instantly updates your CRM and schedules a calendar invite. You initialize the connection using `MultiServerMCPClient` to combine SMS automation with database queries in a single, unified agent execution loop. This setup eliminates manual SDR handoffs by automating the entire scheduling pipeline.

Setup guide

Set up Mav 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 Mav 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({
    "mav-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 Mav 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 Mav. 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 Mav 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 Mav MCP in LangChain

Install `langchain-mcp-adapters` and initialize the `MultiServerMCPClient` with your Vinkius endpoint. Retrieve the tools using `client.get_tools()` and pass them directly to your agent constructor to start triggering SMS playbooks.

Yes, every transaction routed through the server registers as a distinct step in your LangChain execution graph. LangSmith traces the complete payload, response time, and token count for every automated text message.

Yes, you can aggregate the server alongside database or CRM servers using the `MultiServerMCPClient`. This allows your agent to fetch lead info from one server and immediately pass it to an SMS playbook.

The adapter runs statelessly by default, but you can maintain persistent context across SMS exchanges by using `client.session()`. This ensures your agent remembers previous qualification steps during long-running conversations.

Vinkius runs the Mav MCP server within a secure, zero-trust V8 Isolate Sandbox that isolates all SMS payloads. Phone numbers and text transcripts are processed ephemerally, ensuring no sensitive lead data is stored permanently on the hosting platform.

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