How to Use the Cocktail API MCP in Pydantic AI

Build type-safe drink applications with strict schema validation using Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Cocktail API 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 Cocktail API with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strictly validated drink schemas on Pydantic AI

This type-safe MCP integration forces every response from the cocktail database to conform to rigid Python schemas. Stop silent failures in your drink applications by validating payloads from `get_classic_margaritas` before your application processes them. If the data from `get_rum_cocktails` contains an unexpected field type, the agent raises a validation error immediately. You catch bad data in development rather than serving broken ingredients to your users.

Unified MCP Server toolsets

This connection uses the unified MCPToolset class to link your Pydantic AI agent to the hosted MCP server URL. Ditch deprecated HTTP classes to simplify your codebase. Your agent gets immediate, typed access to `get_gin_cocktails` and `get_vodka_cocktails` without manual parsing. The framework handles the JSON schema translation under the hood.

Model-agnostic recipe searching

This model-agnostic search setup lets you swap your underlying LLM without rewriting your drink fetching logic. You can change from Claude to a local model while querying `search_cocktails` with the exact same typed interface. Decoupling your models ensures your ingredient auditing system remains portable. Your custom logic for parsing `get_cocktails_by_ingredients` stays intact even if you change model providers next week.

Setup guide

Set up Cocktail API 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": {
        "cocktail-api-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Cocktail API 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 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 Pydantic AI

The framework wraps the tool outputs in Pydantic models. When your agent calls `get_classic_martinis` over MCP, the incoming JSON is validated against strict Python types, ensuring fields like ingredient lists are always clean arrays.

No, Vinkius hosts and manages the server externally. You simply pass the secure Vinkius endpoint URL to MCPToolset, keeping your local environment free of node or docker dependencies.

Your Pydantic AI agent will catch the mismatch during validation. You can define custom validators on your recipe model to filter out specific ingredients returned by `get_cocktails_by_ingredients` before execution.

Yes, Pydantic AI handles both Streamable HTTP and SSE transports. This ensures stable, long-running connections when your agent performs multiple sequential searches.

No logs are kept. Your search queries and ingredient lists are processed in an ephemeral MCP sandbox that is wiped immediately after the request finishes, keeping your recipes 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