How to Use the CocktailFyi MCP in LangChain

Q: Can LangChain handle parallel tool calls with CocktailFyi?

Yes, your agent can run getcocktail and getingredient simultaneously during a single chain run. LangChain handles the parallel execution and merges the outputs for the next step.

Q: Does CocktailFyi support LangChain tracing?

Absolutely, every tool call like listcategories or searchcocktails goes through the standard MCP execution path. You get full visibility into latency and payloads inside LangSmith.

Feed real-time cocktail recipes and prep techniques directly into your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CocktailFyi MCP to LangChain

Create your Vinkius account to connect CocktailFyi 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 CocktailFyi with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let LangChain agents build multi-step cocktail menus

The `list_cocktails` tool feeds raw recipe data straight into your LangChain runnable sequence. Your agent parses the ABV and prep times, then pipes those metrics to the next chain link to filter out high-proof drinks. By monitoring this process inside LangSmith, you trace exactly how the agent decides to trigger `get_cocktail_stats` to balance a menu. You get clear visibility into token costs for every recipe lookup.

Trace ingredient queries through this MCP Server

This MCP Server exposes `get_ingredient` so your agent can verify allergen profiles mid-chain. If a user asks for a gluten-free drink, the agent pulls the profile and immediately branches the execution flow. You see the exact input and output payloads in your LangSmith dashboard. No guessing why an agent chose a specific substitute when `search_cocktails` returned multiple matches.

Run complex bartending reasoning loops

The `list_techniques` tool lets your agent fetch professional preparation methods before writing a custom recipe. It chains this data with `list_guides` to ensure the final output includes proper shaking or stirring instructions. You configure this using the standard LangChain adapter pattern. Evaluating the difficulty rating of a drink allows the agent to pull glossary terms via `list_glossary` to explain complex steps.

Setup guide

Set up CocktailFyi 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 CocktailFyi 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({
    "cocktailfyi-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 CocktailFyi 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 CocktailFyi. 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 CocktailFyi 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 CocktailFyi MCP in LangChain

Install the adapter package and call the tool getter on your client instance. You pass this list directly to your LangChain agent constructor to expose the recipe database.

Yes, your agent can run `get_cocktail` and `get_ingredient` simultaneously during a single chain run. LangChain handles the parallel execution and merges the outputs for the next step.

Absolutely, every tool call like `list_categories` or `search_cocktails` goes through the standard MCP execution path. You get full visibility into latency and payloads inside LangSmith.

Use the client session context to store previous drink selections. This keeps the history active so the model knows what ingredients are already in the virtual bar cart.

Your searches for ingredients and recipes remain inside the Vinkius secure sandbox. No recipe queries or ingredient lists are stored or shared with external parties.

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