How to Use the NotCo MCP in Mastra AI

Q: How do I set up conditional branching for NotCo recipes in Mastra AI?

You define a step in your Mastra workflow that calls runsensorytest. If the simulated taste score falls below your threshold, you branch the workflow to call searchflavormatches and refine the ingredient ratio.

Q: How do I implement human-in-the-loop approvals before saving a formulation?

Use Mastra's requireToolApproval setting on the createformulation tool. This pauses the workflow and alerts a human food scientist to review the plant-based recipe before it gets committed to your production database.

Build automated plant-based formulation pipelines with Mastra AI and NotCo MCP Server molecular 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 Mastra AI

Create your Vinkius account to connect NotCo to Mastra 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 NotCo with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated multi-step formulation workflows

This MCP Server connects `create_formulation` to Mastra AI workflows, letting you build automated pipelines that generate and validate plant-based recipes without manual oversight. If Giuseppe AI suggests a formula that exceeds your budget, Mastra's branching logic catches the failure and immediately requests a cheaper alternative. By linking this with `estimate_cost`, the system automatically runs cost evaluations on every recipe iteration. If the cost is too high, the workflow retries with different plant-based substitutes until it hits your commercial target.

Self-healing ingredient sourcing pipelines

This MCP Server exposes `list_suppliers` to verify that every plant ingredient in your generated recipe is actually purchasable. If a Mastra AI agent finds that a specific cabbage extract supplier is out of stock, it triggers a sub-workflow to search for alternative vendors. The agent uses `get_ingredient` to match the molecular profile of the missing component with available alternatives. This ensures your automated food development pipeline never recommends a recipe that your supply chain team cannot actually source.

Project tracking with automatic retries

This MCP Server uses `create_project` to log every AI-generated recipe directly into your active R&D database. If the network drops while saving a complex recipe, Mastra's built-in exponential backoff retries the connection until the project is safely recorded. You can use `list_projects` to keep your external tracking systems in sync with Giuseppe AI's latest outputs. This background synchronization runs reliably on any cloud provider, keeping your food scientists updated on the latest sensory test results.

Setup guide

Set up NotCo MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All NotCo tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "notco-mcp-client",
  servers: {
    "notco-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "NotCo Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to NotCo tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent NotCo transactions"
);
console.log(result.text);

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 Mastra AI

You define a step in your Mastra workflow that calls `run_sensory_test`. If the simulated taste score falls below your threshold, you branch the workflow to call `search_flavor_matches` and refine the ingredient ratio.

Yes, Mastra AI handles rate limits using automatic retries and exponential backoff. When querying massive datasets via `list_ingredients`, any temporary API throttles from the Giuseppe AI engine are managed in the background without crashing your execution.

No. You initialize the MCP Client, fetch the tool list using `listTools()`, and spread them directly into your agent's tool array. The agent will autonomously decide when to use `analyze_nutrition` or `get_formulation` based on the workflow state.

Use Mastra's `requireToolApproval` setting on the `create_formulation` tool. This pauses the workflow and alerts a human food scientist to review the plant-based recipe before it gets committed to your production database.

Absolutely. The server runs inside an ephemeral, zero-trust V8 sandbox that touches only the specific molecular ingredient profiles you pass to it. Vinkius does not store your proprietary chemical compositions, ensuring your R&D data remains completely 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