PunkAPI MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect PunkAPI through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="PunkAPI Assistant",
instructions=(
"You help users interact with PunkAPI. "
"You have access to 8 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from PunkAPI"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About PunkAPI MCP Server
Connect to PunkAPI and explore BrewDog's DIY Dog beer catalog through natural conversation — completely free, no API key needed.
The OpenAI Agents SDK auto-discovers all 8 tools from PunkAPI through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries PunkAPI, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
What you can do
- Beer Search — Search beers by name, style, ABV, IBU, hops, yeast, malts and food pairing
- Random Beers — Get random beer suggestions for discovery
- Beer Details — Get full details including ingredients, brewing tips and food pairings
- Filter by ABV — Find session beers (low ABV) or strong beers (high ABV)
- Filter by IBU — Find mild or bitter beers based on preference
- Food Pairing — Find beers that pair well with specific foods
- Hop Varieties — Search beers by specific hop varieties
The PunkAPI MCP Server exposes 8 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect PunkAPI to OpenAI Agents SDK via MCP
Follow these steps to integrate the PunkAPI MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 8 tools from PunkAPI
Why Use OpenAI Agents SDK with the PunkAPI MCP Server
OpenAI Agents SDK provides unique advantages when paired with PunkAPI through the Model Context Protocol.
Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
PunkAPI + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the PunkAPI MCP Server delivers measurable value.
Automated workflows: build agents that query PunkAPI, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents. one queries PunkAPI, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through PunkAPI tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query PunkAPI to resolve tickets, look up records, and update statuses without human intervention
PunkAPI MCP Tools for OpenAI Agents SDK (8)
These 8 tools become available when you connect PunkAPI to OpenAI Agents SDK via MCP:
get_all_beers
Supports searching by name, ABV range, IBU range, EBC (color), malts, hops, yeast, food pairing and brewing date range. Returns beer names, descriptions, ABV, IBU, ingredients and food pairing suggestions. Pagination supported with page and per_page parameters. Search BrewDog beers with filters
get_beer_by_id
Returns name, description, ABV, IBU, EBC, first brewed date, tagline, ingredients (malts, hops, yeast), food pairing suggestions, brewers tips and description. Get a specific beer by ID
get_beers_by_abv
Use abv_gt for minimum ABV and abv_lt for maximum ABV. Useful for finding session beers (low ABV) or strong beers (high ABV). Search beers by ABV (alcohol by volume) range
get_beers_by_food
Common pairings include: "cheese", "burger", "spicy", "dessert", "chicken", "fish", "pork", "bbq", "chocolate", "fruit". Returns matching beers with their food pairing suggestions. Search beers by food pairing suggestion
get_beers_by_hops
Common hops include: "Cascade", "Citra", "Mosaic", "Amarillo", "Simcoe", "Galaxy", "Chinook", "Centennial". Returns matching beers with full hop ingredient details. Search beers by hop variety
get_beers_by_ibu
Low IBU (<20) = mild, Medium IBU (20-40) = balanced, High IBU (40-60) = bitter, Very High IBU (>60) = very bitter. Useful for finding beers matching bitterness preference. Search beers by IBU (International Bitterness Units) range
get_beers_by_style
Common styles include: "American IPA", "Scottish Ale", "Belgian IPA", "English IPA", "Porter", "Stout", "Lager", "Pilsner", "Wheat Beer", "Sour". Returns beer names, ABV, IBU and descriptions. Search beers by style
get_random_beer
Useful for discovering new beers. Can return 1-25 random beers at once. Get random beer(s) from the catalog
Example Prompts for PunkAPI in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with PunkAPI immediately.
"Give me a random beer suggestion."
"Find me beers that pair well with cheese."
"Show me all BrewDog IPAs."
Troubleshooting PunkAPI MCP Server with OpenAI Agents SDK
Common issues when connecting PunkAPI to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
PunkAPI + OpenAI Agents SDK FAQ
Common questions about integrating PunkAPI MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect PunkAPI with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect PunkAPI to OpenAI Agents SDK
Get your token, paste the configuration, and start using 8 tools in under 2 minutes. No API key management needed.