How to Use the NotCo MCP in Google ADK

Q: How do I register the NotCo MCP Server tools in the Google ADK?

Initialize the tools using McpToolset with your Vinkius HTTP endpoint. Pass this toolset into your LlmAgent constructor to expose the formulation and sensory testing capabilities to Gemini.

Q: Can Gemini analyze target nutrition profiles using this setup?

Yes, your agent can call listnutritionalprofiles to retrieve target benchmarks and then run analyzenutrition on any generated recipe to ensure it matches dairy or meat standards.

Connect Gemini's long-context reasoning to Giuseppe AI using the Google ADK to analyze complex molecular databases.

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 Google ADK

Create your Vinkius account to connect NotCo to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise-scale ingredient mapping with Google ADK

Feed your massive BigQuery datasets directly into Giuseppe AI to find plant-based alternatives. By wrapping this MCP Server in Google's `McpToolset`, your Gemini-powered agent can scan millions of rows of supply chain data and match them against `list_ingredients`. The Google ADK excels at long-context reasoning, meaning your agent can digest huge documents of sensory feedback. It then uses `search_flavor_matches` to translate that feedback into concrete molecular targets.

Simulate consumer tests using the NotCo MCP Server

Run complex food science simulations directly from your Google Cloud environment. Your agent uses `run_sensory_test` to predict human sensory responses to new plant-based recipes without needing manual lab tests. You can filter which tools are exposed to the agent by setting a `tool_names` limit in the ADK configuration. This keeps your Gemini agent focused strictly on chemistry tools like `get_ingredient` and `list_nutritional_profiles`.

Predict mass-production costs across your supply chain

Connect your R&D pipeline to real-world procurement data. The agent calls `estimate_cost` to predict production expenses and cross-references the results with your enterprise ERP data. If a formulation exceeds your target budget, the agent queries `list_suppliers` to find cheaper alternatives. It then restarts the formulation loop using `create_formulation` until the cost constraints are satisfied.

Setup guide

Set up NotCo MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with NotCo tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="NotCo_agent",
    model="gemini-2.0-flash",
    instruction="You have access to NotCo tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Initialize the tools using `McpToolset` with your Vinkius HTTP endpoint. Pass this toolset into your `LlmAgent` constructor to expose the formulation and sensory testing capabilities to Gemini.

Yes, you can use the optional tool names filter in the Google ADK configuration. This allows you to restrict your agent to specific operations, like only allowing it to read data via `get_ingredient` or `list_ingredients`.

Yes, the ADK supports both transport protocols. For cloud-deployed enterprise agents, using the Streamable HTTP transport with the Vinkius managed endpoint is the most reliable setup.

Yes, your agent can call `list_nutritional_profiles` to retrieve target benchmarks and then run `analyze_nutrition` on any generated recipe to ensure it matches dairy or meat standards.

Your proprietary recipe data, cost estimates, and molecular ingredient profiles are processed in ephemeral, zero-trust V8 sandboxes. No formulation data is used to train Google's foundation models.

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