How to Use the NotCo MCP in Pydantic AI

Q: How do I initialize the NotCo MCP Server in Pydantic AI?

Install the package with pip install "pydantic-ai-slimmcp" and use MCPToolset to connect to your Vinkius HTTP URL. Pass this toolset directly to your Agent instance to expose the formulation tools.

Q: How do I run sensory simulations using Pydantic AI?

Your agent can call runsensorytest to simulate consumer panels. The resulting sensory scores are validated against your Pydantic schemas, ensuring consistent data structures for your R&D dashboard.

Build type-safe plant-based formulation pipelines with Pydantic AI and 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 Pydantic AI

Create your Vinkius account to connect NotCo to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe molecular analysis using Pydantic AI

Stop worrying about silent data corruption in your food science pipelines. When your agent queries `get_ingredient`, Pydantic AI validates the molecular profile data against strict Python types at runtime. If the underlying MCP Server returns a field that doesn't match your schema, the framework fails loudly. This guarantees that your downstream chemistry models always receive clean, validated data from `list_ingredients`.

Validate recipe costs via the NotCo MCP Server

Ensure every plant-based formulation meets your exact nutritional and financial targets. Your agent can call `analyze_nutrition` and validate the protein, fat, and allergen counts before saving the recipe. By using `estimate_cost`, the agent checks the mass-production budget against your predefined Pydantic models. If the cost is too high, the runtime validation catches it immediately, preventing bad formulations from entering your database.

Simulate sensory panels with guaranteed schemas

Run AI-driven sensory tests with predictable output structures. The agent invokes `run_sensory_test` to simulate taste, texture, and melting profiles, returning structured data that fits your exact application needs. You can easily map these test results to your existing project management tools. The agent uses `create_project` to track the formulation's journey from molecular design to simulated consumer acceptance.

Setup guide

Set up NotCo MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "notco-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to NotCo tools.",
)

result = await agent.run("List recent NotCo transactions")
print(result.output)

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 Pydantic AI

Install the package with `pip install "pydantic-ai-slim[mcp]"` and use `MCPToolset` to connect to your Vinkius HTTP URL. Pass this toolset directly to your `Agent` instance to expose the formulation tools.

The framework will raise a validation error immediately. This prevents your agent from processing corrupted molecular profiles or hallucinated cost estimates from `estimate_cost`.

Yes, Pydantic AI is completely model-agnostic. You can connect the plant-based formulation tools to OpenAI, Anthropic, Gemini, or even a local Llama instance running on your machine.

Your agent can call `run_sensory_test` to simulate consumer panels. The resulting sensory scores are validated against your Pydantic schemas, ensuring consistent data structures for your R&D dashboard.

Your molecular profiles, target nutritional benchmarks, and recipe costs are processed in secure, ephemeral V8 isolates. Pydantic AI validates this data locally in your runtime environment, ensuring sensitive R&D assets never persist on external servers.

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