How to Use the NotCo MCP in OpenAI Agents SDK

Q: How do I set up the NotCo MCP Server with the OpenAI Agents SDK?

Install the package using pip install openai-agents and initialize the connection with MCPServerStreamableHttp. Pass this server instance into your Agent constructor using the mcpservers parameter to let your agent auto-discover the formulation tools.

Q: How does the OpenAI Agents SDK handle tool caching for NotCo?

Set cacheToolsList=True when configuring your streamable HTTP connection. This prevents the SDK from repeatedly querying the notco-mcp server for its 14 tools, keeping your agent execution fast and responsive.

Q: Can my agents create new formulation projects automatically?

Absolutely. Your agent can call createproject to spin up a new workspace and then use createformulation to populate it with AI-generated plant-based recipes based on target benchmarks.

Build production-grade agents using the OpenAI Agents SDK to formulate plant-based recipes with Giuseppe AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NotCo MCP to OpenAI Agents SDK

Create your Vinkius account to connect NotCo to OpenAI Agents SDK 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 NotCo with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated flavor matching via OpenAI Agents SDK

Let your agents hunt down the exact plant-based molecular combinations needed to mimic animal proteins. By passing the `notco-mcp` endpoint to your agent, it automatically discovers tools like `search_flavor_matches` to find ingredients that match target profiles. The SDK handles the heavy lifting of agent handoffs. You can have one agent search for ingredients using `list_ingredients` and then hand off the raw molecular data to a specialized formulation agent to build the final recipe.

Run sensory simulations via the NotCo MCP Server

Stop guessing if your plant-based milk will curdle in coffee. This MCP Server lets your agents trigger `run_sensory_test` to simulate how humans perceive the texture and mouthfeel of your new formulation before you even touch a beaker. Because you are deploying to production, the OpenAI Agents SDK lets you set up strict guardrails. It validates the output of `analyze_nutrition` and checks ingredient costs with `estimate_cost` before committing the data to your R&D log.

Track commercial costs and R&D pipelines

Keep your research organized without writing custom API integration code. Your agent can spin up a new product line using `create_project` and track every single iteration using `list_projects` directly from your Python runtime. When your agent generates a recipe, it immediately calls `estimate_cost` to verify the mass production budget. You get real-world supply chain checks through `list_suppliers` to make sure you can actually source the cabbage or pea protein you need.

Setup guide

Set up NotCo MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all NotCo tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives NotCo tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NotCo tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="NotCo Agent",
            instructions="You have access to NotCo tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 NotCo. 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 NotCo 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 NotCo MCP in OpenAI Agents SDK

Install the package using `pip install openai-agents` and initialize the connection with `MCPServerStreamableHttp`. Pass this server instance into your Agent constructor using the `mcp_servers` parameter to let your agent auto-discover the formulation tools.

Yes, you can run multiple simulations concurrently. Your Python agent can trigger `run_sensory_test` across dozens of formulations in parallel, storing the results directly in your active project workspace.

Set `cacheToolsList=True` when configuring your streamable HTTP connection. This prevents the SDK from repeatedly querying the `notco-mcp` server for its 14 tools, keeping your agent execution fast and responsive.

Absolutely. Your agent can call `create_project` to spin up a new workspace and then use `create_formulation` to populate it with AI-generated plant-based recipes based on target benchmarks.

All molecular ingredient profiles and R&D recipe costs are processed inside an isolated V8 sandbox on Vinkius. The OpenAI Agents SDK communicates over encrypted HTTP streams, ensuring your custom plant-based formulations never leak to public models.

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