How to Use the NotCo MCP in AutoGen

Q: How do AutoGen agents debate NotCo recipe costs?

You assign estimatecost to a procurement agent and createformulation to a food science agent. They talk to each other, rejecting expensive plant isolates until they reach a budget-friendly mozzarella alternative.

Q: How do I manage NotCo projects using AutoGen?

Use a coordinator agent to call listprojects and assign specific formulation tasks to sub-agents. The sub-agents then use createproject to track their progress and store successful cabbage-pea recipes.

Q: How do I register the MCP tools with AutoGen?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP endpoint. Pass the resulting tool list directly to your AssistantAgent constructor to give them access to the 14 formulation tools.

Deploy debating AutoGen agents to negotiate costs, nutrition, and sensory profiles using NotCo tools.

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 AutoGen

Create your Vinkius account to connect NotCo 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 NotCo with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent recipe negotiation

The `create_formulation` and `estimate_cost` tools let AutoGen agents negotiate recipe costs against molecular performance. A procurement agent uses cost predictions to keep things cheap, while a food science agent maximizes meltability. These agents challenge each other's recipes in an AutoGen conversation. They negotiate back and forth until they find a pea protein and cabbage juice ratio that satisfies both the budget and the physical texture requirements.

Adversarial sensory testing

The `run_sensory_test` and `search_flavor_matches` tools allow AutoGen agents to debate and refine plant-based flavor profiles. One agent generates a recipe, and a critic agent immediately runs simulations to expose off-notes or texture failures. The critic agent uses this MCP tool feedback to demand changes. This conversational loop continues until the recipe passes the simulated sensory threshold, ensuring only viable formulations reach physical bench testing.

Project-aligned nutrition planning

The `list_projects` and `analyze_nutrition` tools let AutoGen coordinate high-level R&D goals across multiple specialized agents. A project manager agent tracks active goals and assigns target profiles to formulation agents. The formulation agents use nutritional analysis to verify their designs against those targets. AutoGen coordinates this multi-agent workflow, ensuring that every cabbage-pea formulation aligns with your high-level R&D roadmap.

Setup guide

Set up NotCo 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 NotCo 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="NotCo_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You assign `estimate_cost` to a procurement agent and `create_formulation` to a food science agent. They talk to each other, rejecting expensive plant isolates until they reach a budget-friendly mozzarella alternative.

Yes. A formulation agent can design a recipe and hand it off to a sensory agent to execute `run_sensory_test`. If the simulated elasticity score is too low, the sensory agent requests a recipe revision.

Use a coordinator agent to call `list_projects` and assign specific formulation tasks to sub-agents. The sub-agents then use `create_project` to track their progress and store successful cabbage-pea recipes.

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your Vinkius HTTP endpoint. Pass the resulting tool list directly to your `AssistantAgent` constructor to give them access to the 14 formulation tools.

Yes. Your cost estimates and supplier lists are processed in isolated, single-tenant V8 execution environments. Vinkius handles all authentication securely, ensuring your financial data never leaks to other users.

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