Bring Food Tech
to Pydantic AI
Learn how to connect NotCo to Pydantic AI and start using 14 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for Subscribers
What is the NotCo MCP Server?
Connect your AI agent directly to Giuseppe, NotCo’s proprietary Food Tech AI platform. Accelerate your B2B food research and development by commanding Giuseppe through natural language.
What you can do
- AI Formulation Generation — Command Giuseppe to analyze the molecular structure of an animal product and generate a plant-based blueprint using combinations from a database of over 300,000 plants
- Ingredient Search — Browse and retrieve the molecular, sensory, and functional profiles of thousands of plant extracts and proteins
- Flavor & Texture Matching — Use AI computational models to find plant compounds that replicate specific volatile molecules, aromas, and mouthfeels
- Nutritional Label Prediction — Run predictive algorithms on custom plant mixtures to estimate the final nutritional values of a recipe before entering the lab
- Cost Estimation — Predict the theoretical mass-production cost of an AI-generated formula based on global commodity pricing
How it works
1. Subscribe to this server
2. Enter your NotCo API Key (partner access required)
3. Start exploring formulations from Claude, Cursor, or your preferred MCP client
Who is this for?
- Food Scientists & R&D Teams — instantly query molecular matches without switching contexts
- Product Formulators — test theoretical plant-based recipes in a virtual environment before lab prototyping
- Strategic Food Partners — monitor project progress and evaluate AI-generated prototypes rapidly
Built-in capabilities (14)
Analyze the nutritional output of a formulation
Request a new AI formulation
Create a new R&D project
Predict the mass production cost of a formulation
Get details of a specific AI formulation
Get complete molecular profile of an ingredient
g., dairy, meat, sauces). List plant-based AI formulations
Search the plant-based ingredient molecular database
List target nutritional benchmarks
List active R&D projects
List standard sensory profiles
List approved ingredient suppliers
Run an AI simulation of a sensory test
Find plant combinations that mimic a target flavor
Why Pydantic AI?
Pydantic AI validates every NotCo tool response against typed schemas, catching data inconsistencies at build time. Connect 14 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your NotCo integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your NotCo connection logic from agent behavior for testable, maintainable code
NotCo in Pydantic AI
NotCo and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect NotCo to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for NotCo in Pydantic AI
The NotCo 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. All 14 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
NotCo for Pydantic AI
Every tool call from Pydantic AI to the NotCo MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I use this to generate a formula for a new plant-based meat?
Yes! Use the create_formulation tool to instruct Giuseppe to model a specific animal product (e.g., 'Target: Pulled Pork'). You can pass constraints like 'no soy' or 'must contain pea protein'. Giuseppe will return a mathematically generated formula combining plant extracts that mimic the target's molecular profile.
How does Giuseppe match specific flavors?
The search_flavor_matches tool analyzes NotCo's proprietary database. Instead of searching for 'beef flavor', Giuseppe searches for the specific volatile molecular compounds that create the beef flavor, and then finds combinations of seemingly unrelated plants (like pineapple and cabbage) that, when combined mathematically, replicate that exact molecular behavior.
Can I predict the cost of a new formulation before making it?
Absolutely. Once Giuseppe generates a formulation, you can pass its ID to the estimate_cost tool. The API cross-references the required plant ingredients with global B2B commodity pricing databases to give you an estimated per-kilogram cost for mass production.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your NotCo MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai