How to Use the CocktailFyi MCP in AutoGen

Q: Can agents search for custom drink guides?

Yes, agents use listguides and listglossary to find relevant educational content. This helps them explain complex bartending terms during their conversation.

Let autonomous AutoGen agents debate recipe ratios, ingredient pairings, and prep techniques.

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 AutoGen

Create your Vinkius account to connect CocktailFyi 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 CocktailFyi with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate cocktail recipes

This MCP Server allows your AutoGen agents to collaborate on menu creation. A mixologist agent uses `get_cocktail` to pull a classic recipe, while a finance agent checks the cost of ingredients. They negotiate the final menu structure using metrics from `get_cocktail_stats`. The agents debate the optimal ABV balance before finalizing the list.

Verify ingredients via multi-agent debate

The `get_ingredient` tool gives your agents the exact flavor profiles needed to argue about pairings. One agent suggests an ingredient, while another uses `list_ingredients` to check for conflicts or allergens. You register these tools with the assistant agent using the standard adapter. The agents run `search_cocktails` to find historical precedents for unusual flavor combinations.

Let agents audit preparation techniques

The `list_techniques` tool provides the raw instructions that your quality-assurance agent uses to review recipes. It verifies if a drink requires shaking or stirring based on the ingredients listed. The agent compares these steps against `list_guides` to ensure the instructions are clear. If there is an issue, it asks the writer agent to revise the text before outputting the final recipe.

Setup guide

Set up CocktailFyi 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 CocktailFyi 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="CocktailFyi_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent CocktailFyi 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="CocktailFyi_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent CocktailFyi 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 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 AutoGen

Use the MCP tool helper from the AutoGen extension package. Pass the Vinkius URL to register tools like `list_cocktails` directly to your assistant agent.

Yes, the agents share access to the toolset. One agent can call `get_cocktails_by_category` while another calls `list_faqs` to resolve a debate about a drink's history.

The AutoGen MCP tool adapter automatically converts the tool schemas. Tools like `get_cocktail` map directly to the function calling format expected by your agents.

Yes, agents use `list_guides` and `list_glossary` to find relevant educational content. This helps them explain complex bartending terms during their conversation.

No, the cocktail recipes and ingredient lists processed during agent debates remain private. The Vinkius MCP integration runs on a zero-trust model, meaning no execution data is persisted.

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