How to Use the NotCo MCP in CrewAI

Q: How do I pass NotCo tools to a specific agent in CrewAI?

You can pass the MCP Server URL directly into the agent's mcps list during initialization. This gives that specific agent access to tools like getingredient and createformulation while keeping other agents focused on pure text analysis.

Q: Can I restrict which NotCo tools my CrewAI agents can access?

Yes, you can use MCPServerHTTP from crewai.mcp along with a toolfilter. This allows you to restrict your Cost Estimator agent to only see estimatecost, while your Culinary agent gets access to searchflavormatches.

Q: How is my proprietary nutritional benchmark data protected?

All nutritional benchmarks queried via listnutritionalprofiles are protected by Vinkius's zero-trust architecture. The server operates in an ephemeral environment, meaning your target nutrition profiles are never cached, logged, or exposed to third parties.

Deploy specialized teams of AI food scientists to design plant-based recipes autonomously using CrewAI and this NotCo MCP Server.

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 CrewAI

Create your Vinkius account to connect NotCo to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized AI food scientist crews

This MCP Server enables your CrewAI agents to use `search_flavor_matches` to divide and conquer complex plant-based recipe development. You can assign one agent the role of Flavor Researcher to find plant combinations, while a second agent acts as a Nutritionist to evaluate the health profiles. The Nutritionist agent uses `analyze_nutrition` to verify that the plant-based milk or meat alternative matches target benchmarks. Because the agents share memory, they collaborate iteratively until they find a formula that tastes right and hits the exact nutritional goals.

Autonomous sensory and cost validation

This MCP Server exposes `run_sensory_test` so a simulated tasting agent can evaluate recipes generated by other crew members. If the sensory agent detects an off-note flavor or texture issue, it sends the recipe back to the formulator agent with specific feedback. Meanwhile, a Procurement agent uses `estimate_cost` to ensure the recipe is financially viable. This multi-agent feedback loop mimics a real food R&D department, refining the plant-based product autonomously before any physical kitchen tests begin.

Structured food R&D project management

This MCP Server uses `create_project` to allow a Manager agent to organize and track multiple plant-based formulation campaigns. The Manager agent coordinates the work of the researchers and ensures all successful formulas are logged under the correct R&D initiative. By calling `list_projects`, the crew maintains a shared context of what formulations have already been attempted. This prevents agents from repeating failed experiments and ensures the entire team is working toward active product development goals.

Setup guide

Set up NotCo MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke NotCo tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="NotCo Analyst",
    goal="Access and analyze NotCo data via MCP.",
    backstory="Expert analyst with direct NotCo access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent NotCo transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="NotCo Analyst",
        goal="Access and analyze NotCo data via MCP.",
        backstory="Expert analyst with direct NotCo access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent NotCo transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can pass the MCP Server URL directly into the agent's `mcps` list during initialization. This gives that specific agent access to tools like `get_ingredient` and `create_formulation` while keeping other agents focused on pure text analysis.

Yes, you can use `MCPServerHTTP` from `crewai.mcp` along with a `tool_filter`. This allows you to restrict your Cost Estimator agent to only see `estimate_cost`, while your Culinary agent gets access to `search_flavor_matches`.

You set up a sequential crew where the first agent searches for ingredients using `list_ingredients`, the second agent generates the recipe via `create_formulation`, and the third agent runs sensory simulations. They pass the data down the line automatically.

We recommend using the Streamable HTTP transport hosted by Vinkius for direct integration. It handles all the underlying authentication and connection pooling, so your Python-based agents can query the Giuseppe AI engine without lag.

All nutritional benchmarks queried via `list_nutritional_profiles` are protected by Vinkius's zero-trust architecture. The server operates in an ephemeral environment, meaning your target nutrition profiles are never cached, logged, or exposed to third parties.

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