How to Use the CocktailFyi MCP in Pydantic AI

Build type-safe mixology applications using Pydantic AI and verified cocktail schemas.

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 Pydantic AI

Create your Vinkius account to connect CocktailFyi to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict runtime validation for Pydantic AI drink recipes

The `get_cocktail` tool pulls drink details directly into your runtime to avoid silent failures when parsing recipes. When your agent calls this tool, Pydantic AI validates every returned field—like ABV, calories, and glass type—against strict Python types. If the underlying API ever returns a null value where a string is expected, your agent fails immediately rather than passing bad instructions to a user. This guarantees that your drink preparation steps are always accurate.

Type-safe search and categorization

The `search_cocktails` tool finds recipes by name or ingredient with complete structural confidence. The returned dataset is parsed into validated Pydantic models before your agent even reads it. You can also use `get_cocktails_by_category` to build filtered lists. This MCP Server ensures that every drink in the category conforms to the exact schema your application expects.

Verified ingredient and technique lookups

The `list_techniques` tool fetches the correct methods when your agent needs to explain how to prepare a drink. The framework validates the step-by-step instructions to prevent formatting errors. For inventory checks, `get_ingredient` returns structured data about specific items. This makes it easy to write type-safe logic that subtracts stock when a drink is ordered.

Setup guide

Set up CocktailFyi MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "cocktailfyi-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to CocktailFyi tools.",
)

result = await agent.run("List recent CocktailFyi transactions")
print(result.output)

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 Pydantic AI

Instantiating the connection is simple. Use the toolset class with your Vinkius HTTP endpoint, then pass it directly into your agent toolsets list.

The framework will raise a validation error immediately. This prevents your agent from hallucinating recipe steps or serving drinks with incorrect ingredients.

Yes. Since the framework is model-agnostic, you can route validated tools like `list_ingredients` to local models or commercial APIs.

Yes, the server must be running externally. Vinkius hosts the endpoint, and your agent connects via SSE or Streamable HTTP transports.

All validation happens locally in your runtime, while Vinkius handles the API requests in a zero-trust environment. Your search strings and ingredient queries are processed ephemerally and never stored.

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