How to Use the NotCo MCP in LangChain

Q: How does LangChain track NotCo formulation costs?

You can build a LangChain chain that calls estimatecost immediately after generating a recipe. This lets your agent reject expensive ingredients and query listsuppliers for cheaper alternatives before finalizing the run.

Q: Can LangChain run NotCo sensory simulations autonomously?

Yes. Your LangChain agent can call runsensorytest as a validation step in your chain. If the simulated elasticity score is too low, the agent loops back to createformulation to try a different emulsion.

Q: How do I connect the NotCo MCP Server to LangChain?

Install the adapter package and use MultiServerMCPClient pointing to your Vinkius HTTP endpoint. Once connected, call client.gettools() to pass the 14 food science tools directly to your LangChain agent.

Build multi-step plant-based food formulation chains in LangChain using NotCo's MCP Server.

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 LangChain

Create your Vinkius account to connect NotCo to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain-linked molecular recipe development

The `list_ingredients` and `create_formulation` tools let LangChain agents feed molecular data directly into new recipe requests. Your agent queries the plant database for high-protein isolates, passes those candidates to the formulation engine, and checks the nutrition profile in a single run. This chain setup removes manual data transfer between steps. LangSmith traces each tool transition, letting you see exactly how the agent adjusted the pea protein ratio to match your target amino acid profile.

Cost-aware formulation loops

The `estimate_cost` and `list_suppliers` tools let your LangChain agent run budget-aware formulation loops autonomously. The agent starts by generating a recipe, evaluates the financial impact, and swaps out expensive ingredients if the budget is blown. This loop runs without manual intervention. The agent checks the final recipe against `list_nutritional_profiles` to guarantee you do not trade nutritional value for a cheaper bill of materials.

Automated sensory validation

The `run_sensory_test` and `search_flavor_matches` tools allow LangChain agents to run simulated taste tests on plant-based emulsions. Your agent triggers simulated panels to see how a human would react to the texture of a cabbage juice setup before you mix it in the kitchen. If the texture scores fall short, the chain automatically finds plant-based compounds that fix the off-notes. This integration cuts down bench testing cycles by weeding out bad formulations early.

Setup guide

Set up NotCo MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes NotCo tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "notco-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent NotCo transactions"
    })
    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 LangChain

Yes. LangChain agents use the tools to run sequential tasks, like calling `list_ingredients` and then passing those molecular profiles straight into `create_formulation` without manual intervention.

You can build a LangChain chain that calls `estimate_cost` immediately after generating a recipe. This lets your agent reject expensive ingredients and query `list_suppliers` for cheaper alternatives before finalizing the run.

Yes. Your LangChain agent can call `run_sensory_test` as a validation step in your chain. If the simulated elasticity score is too low, the agent loops back to `create_formulation` to try a different emulsion.

Install the adapter package and use `MultiServerMCPClient` pointing to your Vinkius HTTP endpoint. Once connected, call `client.get_tools()` to pass the 14 food science tools directly to your LangChain agent.

Your custom recipe inputs and molecular data never persist on public servers. Vinkius runs the server inside isolated, ephemeral V8 sandboxes, ensuring your proprietary plant-based formulations are destroyed the moment your session ends.

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