OpenTHC MCP Server for CrewAI 12 tools — connect in under 2 minutes
Connect your CrewAI agents to OpenTHC through Vinkius, pass the Edge URL in the `mcps` parameter and every OpenTHC tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
from crewai import Agent, Task, Crew
agent = Agent(
role="OpenTHC Specialist",
goal="Help users interact with OpenTHC effectively",
backstory=(
"You are an expert at leveraging OpenTHC tools "
"for automation and data analysis."
),
# Your Vinkius token. get it at cloud.vinkius.com
mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)
task = Task(
description=(
"Explore all available tools in OpenTHC "
"and summarize their capabilities."
),
agent=agent,
expected_output=(
"A detailed summary of 12 available tools "
"and what they can do."
),
)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)
* 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
About OpenTHC MCP Server
Connect your OpenTHC Cannabis Regulatory Compliance Engine to any AI agent and take full control of your seed-to-sale workflows through natural conversation.
When paired with CrewAI, OpenTHC becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call OpenTHC tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
What you can do
- Company & License Management — List all registered companies and verify active cannabis licenses for compliance assurance
- Cultivation Tracking — Query all active plants in cultivation with growth stages, strain varieties, and facility room locations
- Inventory Control — Fetch complete inventory ledger including harvested material, work-in-progress, finished goods, and destruction candidates
- Laboratory Testing — Access lab samples and Certificates of Analysis (CoA) with full potency, terpene, and contaminant test results
- B2B Transfers — Monitor incoming and outgoing wholesale transfer orders with manifests, bills of lading, and fulfillment status
- Retail Sales — Retrieve point-of-sale B2C transaction history for daily reporting, tax verification, and purchase limit enforcement
- Product Catalog — Browse your complete cannabis product catalog with THC/CBD percentages, SKU data, and regulatory classifications
- Facility Organization — List cultivation rooms, processing areas, and operational zones for spatial inventory and workflow planning
The OpenTHC MCP Server exposes 12 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect OpenTHC to CrewAI via MCP
Follow these steps to integrate the OpenTHC MCP Server with CrewAI.
Install CrewAI
Run pip install crewai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Customize the agent
Adjust the role, goal, and backstory to fit your use case
Run the crew
Run python crew.py. CrewAI auto-discovers 12 tools from OpenTHC
Why Use CrewAI with the OpenTHC MCP Server
CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with OpenTHC through the Model Context Protocol.
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 `mcps` parameter 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
OpenTHC + CrewAI Use Cases
Practical scenarios where CrewAI combined with the OpenTHC MCP Server delivers measurable value.
Automated multi-step research: a reconnaissance agent queries OpenTHC for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff
Scheduled intelligence reports: set up a crew that periodically queries OpenTHC, analyzes trends over time, and generates executive briefings in markdown or PDF format
Multi-source enrichment pipelines: chain OpenTHC tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow
Compliance and audit automation: a compliance agent queries OpenTHC against predefined policy rules, generates deviation reports, and routes findings to the appropriate team
OpenTHC MCP Tools for CrewAI (12)
These 12 tools become available when you connect OpenTHC to CrewAI via MCP:
list_b2b_transactions
Each B2B transaction record contains the transfer ID, direction (incoming/outgoing), counterparty company, transfer status (draft, committed, received, rejected), creation date, expected fulfillment date, line items with quantities, and attached manifests or bills of lading. Essential for supply chain orchestration, logistics planning, and regulatory transfer documentation. AI agents use this to track shipment status, verify received quantities, and prepare compliance reports. List all B2B transfer transactions (incoming and outgoing)
list_b2c_transactions
Each transaction includes the sale ID, customer information (if recorded), sale date, line items with products and quantities, total amount, tax breakdown, dispensary location, and inventory deduction confirmations. Critical for daily sales reporting, tax calculation verification, inventory reconciliation, and regulatory sales limit enforcement. AI agents should query this to analyze sales patterns, verify compliance with purchase limits, and prepare end-of-day reports. List all retail B2C sales transactions
list_companies
Use this to understand which organizations are part of your regulatory network, including license holders, cultivators, processors, distributors, and retailers. Each company record contains legal identification data, registration status, and associated license information. Essential for multi-company operations and B2B transaction verification. List all companies registered in the OpenTHC compliance engine
list_contacts
Each contact includes company affiliation, contact type (B2B partner, regulatory agency, logistics provider), communication details, and relationship status. Use this to identify verified trading partners before creating B2B transfer orders or compliance documentation. List all business contacts in the OpenTHC network
list_inventory
Each inventory item displays the lot number, item type, quantity with unit of measurement, storage location, creation date, chain of custody history, and compliance status. Fundamental for stock reconciliation, audit preparation, transfer order creation, and regulatory reporting. AI agents should query this before fulfilling orders or conducting inventory audits. List all inventory items with quantities and locations
list_lab_results
Each result includes the lab result ID, linked sample, testing laboratory accreditation, full analytical results (THC/CBD potency, terpene profile, contaminant levels), pass/fail determination, and the official CoA document reference. Critical for regulatory compliance, product labeling accuracy, retail menu display, and consumer transparency. AI agents should reference this to verify product safety before sale or transfer. List all laboratory test results and certificates of analysis
list_lab_samples
Each sample contains the sample ID, linked inventory lot, sample type (flower, edible, concentrate), test panel requested (potency, pesticides, heavy metals, mycotoxins, microbials, residual solvents), submission date, testing laboratory, and current analysis status. Essential for quality assurance workflows, batch release decisions, and compliance with mandatory testing regulations. AI agents should check this to determine if a batch has pending or cleared lab results. List all laboratory samples submitted for testing
list_licenses
Each license contains the license type, expiration dates, regulatory conditions, and approval status. Critical for compliance verification — AI agents should check this before initiating any regulated activity to ensure the proper license is active and valid for the intended operation. List all cannabis licenses associated with your account
list_plants
Each plant record contains the unique plant ID (POP/PIP tags), growth stage (vegetative, flowering, harvesting), strain/variety, location within the facility (room, rack, shelf), planting date, and estimated harvest window. Critical for cultivation management, compliance reporting, and seed-to-sale traceability. AI agents use this to monitor crop health, predict harvest timelines, and ensure regulatory plant count limits are respected. List all cannabis plants in active cultivation
list_products
Each product entry contains the product name, type classification, SKU, potency information (THC/CBD percentages), package sizes, and regulatory tags. Essential for retail operations, menu generation, and B2B sales order creation. AI agents should reference this when checking product availability or creating sales transactions. List all cannabis products in your inventory catalog
list_sections
Each section entry includes the section ID, name, purpose classification (vegetation room, flowering room, drying room, processing area, retail floor, warehouse), environmental parameters, and capacity limits. Essential for spatial inventory tracking, cultivation workflow organization, facility compliance inspections, and operational planning. AI agents use this to assign plants to specific rooms during cultivation activities, locate inventory within the facility, and generate room-level production reports. List all facility sections and cultivation areas
list_varieties
Each variety record contains the variety ID, strain name (e.g., Blue Dream, OG Kush, Sour Diesel), genetics type (Type I - THC dominant, Type II - Mixed THC/CBD, Type III - CBD dominant), breeder information, and associated cultivation characteristics. Fundamental for cultivation planning, product labeling, genetic tracking, and regulatory strain registration. AI agents reference this when creating new plant records, generating product labels, or analyzing strain performance metrics. List all cannabis varieties (strains) in the system
Example Prompts for OpenTHC in CrewAI
Ready-to-use prompts you can give your CrewAI agent to start working with OpenTHC immediately.
"List all our active cannabis licenses and verify which ones are expiring soon."
"Show me all plants currently in flowering stage in Room 3 and estimate harvest readiness."
"Check inventory levels for all THC-dominant flower products and show me pending lab results."
Troubleshooting OpenTHC MCP Server with CrewAI
Common issues when connecting OpenTHC to CrewAI through the Vinkius, and how to resolve them.
MCP tools not discovered
Agent not using tools
Timeout errors
Rate limiting or 429 errors
OpenTHC + CrewAI FAQ
Common questions about integrating OpenTHC MCP Server with CrewAI.
How does CrewAI discover and connect to MCP tools?
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?
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?
Can CrewAI agents call multiple MCP tools in parallel?
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)?
crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.Connect OpenTHC with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect OpenTHC to CrewAI
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.