Bring Food Tech
to CrewAI
Learn how to connect NotCo to CrewAI 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 CrewAI?
When paired with CrewAI, NotCo becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call NotCo tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
- —
Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools
- —
CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the
mcpsparameter and agents auto-discover every available tool at runtime - —
Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls
- —
Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports
NotCo in CrewAI
NotCo and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect NotCo to CrewAI 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 CrewAI
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 CrewAI 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 CrewAI
Every tool call from CrewAI 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 CrewAI discover and connect to MCP tools?
CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.
Can different agents in the same crew use different MCP servers?
Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.
What happens when an MCP tool call fails during a crew run?
CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.
Can CrewAI agents call multiple MCP tools in parallel?
CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.
Can I run CrewAI crews on a schedule (cron)?
Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.
MCP tools not discovered
Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.
Agent not using tools
Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".
Timeout errors
CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.
Rate limiting or 429 errors
Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.