How to Use the NotCo MCP in LlamaIndex

Q: How does LlamaIndex store NotCo ingredient profiles?

LlamaIndex converts the molecular data returned by getingredient into vector embeddings. This lets you run semantic queries over your plant-based database to find structural matches for animal proteins.

Q: Can I query past NotCo sensory tests using LlamaIndex?

Yes. By indexing the output of runsensorytest, LlamaIndex allows you to search historical simulation results. You can query past runs to see which cabbage juice concentrations yielded the best meltability scores.

Q: How do I initialize the MCP tools in LlamaIndex?

Use llama-index-tools-mcp to initialize the client with your Vinkius HTTP endpoint. Convert the client into tool specs and pass them to your FunctionAgent to start running formulations.

Index NotCo molecular food data and sensory test outputs directly into your LlamaIndex knowledge base.

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 LlamaIndex

Create your Vinkius account to connect NotCo to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic search over NotCo molecular databases

The `list_ingredients` and `get_ingredient` tools let LlamaIndex index molecular profiles directly into your vector database. When your agent queries the molecular database, the retrieved profiles are indexed immediately, letting you run semantic searches over plant structures. This turns transient API calls into a queryable knowledge base. You can ask your LlamaIndex application which plant proteins match casein's micelle structure, and it will answer using cached data from previous runs.

Grounded sensory analysis with LlamaIndex RAG

The `run_sensory_test` and `list_sensory_profiles` tools allow LlamaIndex agents to ground recipe adjustments in simulated physical data. By indexing the results of taste simulations, LlamaIndex ensures every recipe modification is backed by physical data, not model hallucinations. The agent queries this indexed sensory history before running `create_formulation`. This prevents the model from suggesting plant-based mixtures that have already failed texture or elasticity tests.

Cost optimization with LlamaIndex

The `list_suppliers` and `estimate_cost` tools let your LlamaIndex agent build a localized database of regional ingredient pricing. The agent queries these tools to build a cost index for cabbage juice and pea protein. This setup lets your agent cross-reference active projects from `list_projects` with current ingredient costs. The system finds cheaper regional suppliers without compromising the target nutrition profile.

Setup guide

Set up NotCo MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all NotCo MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to NotCo tools.",
)
response = await agent.run("List recent NotCo data")

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 LlamaIndex

LlamaIndex converts the molecular data returned by `get_ingredient` into vector embeddings. This lets you run semantic queries over your plant-based database to find structural matches for animal proteins.

Yes. By indexing the output of `run_sensory_test`, LlamaIndex allows you to search historical simulation results. You can query past runs to see which cabbage juice concentrations yielded the best meltability scores.

LlamaIndex indexes your R&D history by fetching active files via `list_projects`. This lets your agent cross-reference new formulations with historical project notes to prevent duplicate R&D efforts.

Use `llama-index-tools-mcp` to initialize the client with your Vinkius HTTP endpoint. Convert the client into tool specs and pass them to your `FunctionAgent` to start running formulations.

All molecular queries and sensory simulation logs are processed in secure, zero-trust environments. Vinkius ensures that no raw data is used to train public models, keeping your plant-based IP entirely private.

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