How to Use the Cocktail API MCP in AutoGen

Q: How do AutoGen agents share access to the Cocktail API tools?

You register tools like searchcocktails with the AssistantAgent constructor. This allows any agent in your conversational group to trigger a recipe search during their debate.

Q: Can one AutoGen agent pass Cocktail API results to another?

Yes, an agent can call getgincocktails and pass the raw ingredient list directly to a critic agent. The critic agent then evaluates the proportions in the next turn of the conversation.

Let your AutoGen agents debate and refine cocktail recipes using real-time ingredient data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cocktail API MCP to AutoGen

Create your Vinkius account to connect Cocktail API to AutoGen 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 Cocktail API with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate classic margarita variations in AutoGen

The `get_classic_margaritas` tool fetches precise tequila and lime proportions for your multi-agent conversations. One AutoGen agent can suggest a recipe, while a critic agent reviews the ingredients to debate the perfect sour-to-sweet ratio. This collaborative setup ensures your drink recommendations are thoroughly vetted. The agents use the output of `get_tequila_cocktails` to cross-reference historical recipes and reach a consensus on the ultimate build.

Coordinate complex drink menus with this MCP Server

The `get_cocktails_by_ingredients` tool lets your agent cluster decide which drinks to feature on a menu based on available stock. Your AutoGen supervisor agent assigns the search task to a specialized mixology agent. By integrating this MCP Server, your agents can coordinate searches across `get_rum_cocktails` and `get_vodka_cocktails` simultaneously. They negotiate which recipes use the inventory most efficiently before presenting the final drink list.

Audit martini instructions via multi-agent debate

The `get_classic_martinis` tool delivers exact mixing steps to your conversational agents. A preparation agent reads the instructions, while a safety agent analyzes the steps to ensure proper handling of glass and ice. If the instructions returned by `search_cocktails` seem vague, the agents discuss alternatives. They query the API again to clarify ratios, ensuring the final output is a highly polished, step-by-step recipe.

Setup guide

Set up Cocktail API MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Cocktail API tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Cocktail API_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Cocktail API data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Cocktail API_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Cocktail API data")
    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 Cocktail API. 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 Cocktail API 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 Cocktail API MCP in AutoGen

You register tools like `search_cocktails` with the AssistantAgent constructor. This allows any agent in your conversational group to trigger a recipe search during their debate.

Yes, an agent can call `get_gin_cocktails` and pass the raw ingredient list directly to a critic agent. The critic agent then evaluates the proportions in the next turn of the conversation.

The McpToolAdapter automatically translates the schema of tools like `get_rum_cocktails` into the format AutoGen expects. You do not have to write custom JSON schemas for your agents.

Yes, you can connect your agents via stdio or streamable HTTP. Vinkius handles the connection hosting so your multi-agent system can query recipes reliably.

Yes, all data transmission containing ingredients and instructions is encrypted in transit. Vinkius uses zero-trust architecture, ensuring that no conversational history or recipe data leaks outside your active session.

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