How to Use the Untappd MCP in LangChain

Build complex, multi-step beer tracking and social logic using your AI client and the Untappd 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 Untappd MCP to LangChain

Create your Vinkius account to connect Untappd 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 Untappd with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Step Beer Tracking with LangChain

Your agent can build entire reasoning chains around a single goal. For instance, you can search for beers using `search_beer`, then check the detailed information for one via `get_beer_info`. The output of the first call feeds directly into determining which beer to recommend.

Managing Social Profiles with MCP Server

Need to manage a friend's activity or your own social feed? You can check pending requests using `get_pending_friends` and then decide whether to accept them with `accept_friend`. This pattern lets you build conversational logic around maintaining connections.

Contextualizing User Activity for LangChain

The system handles complex data flows, moving from high-level user data down to specific check-in details. Get a friend's activity feed using `get_friend_activity`, then pull extended context with `get_checkin_details` to know where and when they were drinking it.

Setup guide

Set up Untappd 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 Untappd 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({
    "untappd-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 Untappd 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 Untappd. 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 Untappd 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 Untappd MCP in LangChain

When you run an agent using LangChain, the MCP Server exposes all its tools. Your client decides which tool to call—like `get_user_info` or `search_brewery`—and passes the parameters directly.

Yes, the setup supports aggregating multiple MCP servers. This means your single agent can pull data from several sources, not just Untappd, within one continuous chain.

You can build a sequence that first gets all distinct beers a user has had via `get_user_distinct_beers`. Then, you pass those results into another tool call within the chain for further processing.

Absolutely. Vinkius handles authentication through a single endpoint token, keeping your interactions with the MCP Server isolated and zero-trust by design.

This server manages various types of user activity, including `user profile information`, friend connection statuses (`get_pending_friends`), and detailed check-in records (`get_checkin_details`).

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