How to Use the CocktailFyi MCP in OpenAI Agents SDK

Q: Can I use CocktailFyi to filter drinks by ABV in my OpenAI Agents SDK pipeline?

Yes. Your agent can query listcocktails and inspect the ABV field in the returned data. This lets you enforce safety guards on alcohol content before returning responses.

Build production-grade beverage agents with OpenAI Agents SDK and real-time mixology data.

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 OpenAI Agents SDK

Create your Vinkius account to connect CocktailFyi to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Verify recipes before your OpenAI Agents SDK agent serves them

The `get_cocktail` tool prevents your automated bartender from guessing drink specs by pulling exact recipe details directly into your OpenAI Agents SDK runtime. This means your agent can inspect drink details and verify the ABV before approving a recipe for a user. Verify recipes before your OpenAI Agents SDK agent serves them using this MCP Server. If a user asks for something low-alcohol, the agent uses `get_cocktails_by_category` to filter options. Running these checks inside the SDK's built-in guardrails ensures the agent never suggests a high-proof drink by mistake.

Structured inventory and preparation guides

The `list_techniques` tool provides the exact preparation methods needed to build a drink, letting your agent understand when to shake, stir, or muddle. It maps these techniques to specific cocktails to build a step-by-step prep guide for your staff. To keep stock under control, the agent calls `get_ingredient` to inspect specific items. It cross-references what is in your inventory with the required ingredients before starting the mixing instructions.

Smart cocktail search with tracing

The `search_cocktails` tool finds matches across names, ingredients, and guide titles when users ask for vague recipes. The OpenAI dashboard traces this tool call, showing you exactly how the agent parsed the user's messy text. You can also use `list_cocktails` to paginate through the entire database. This MCP Server lets you paginate through the entire database, letting your agent build structured menus while caching the tools list to keep latency low.

Setup guide

Set up CocktailFyi MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CocktailFyi tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CocktailFyi tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CocktailFyi tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CocktailFyi Agent",
            instructions="You have access to CocktailFyi tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and import the streamable HTTP server parameters. Pass the Vinkius endpoint URL to the Agent constructor, and the SDK will auto-discover tools like `get_cocktail` instantly.

Yes. Your agent can query `list_cocktails` and inspect the ABV field in the returned data. This lets you enforce safety guards on alcohol content before returning responses.

If a tool call fails, the SDK captures the exception. You can inspect the failure in your trace dashboard to see if the query to `search_cocktails` was malformed.

Yes. You should set the cache parameter to true in your SDK configuration. This prevents the agent from querying the tools schema on every single message turn.

Vinkius runs this MCP Server in an isolated sandbox. Your search queries and ingredient checks are never stored or used to train models, keeping your custom drink menus secure.

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