How to Use the NCR Voyix MCP in CrewAI

Q: How do multiple CrewAI agents share NCR Voyix MCP tool access?

You pass the Vinkius URL directly in the mcps array of your CrewAI configuration to share the MCP Server. This allows your inventory agent to call listinventory while your sales agent simultaneously calls listorders within the same execution loop.

Q: Can I restrict specific CrewAI agents from accessing sensitive NCR Voyix data?

Yes, you can use MCPServerHTTP with a toolfilter to limit tool exposure. This ensures your customer support agent can only access listcustomers while your warehouse agent is restricted to listinventory and getsite.

Q: How is customer transaction data secured during multi-agent CrewAI runs?

All transaction details retrieved via getorder are processed in ephemeral memory and never written to persistent logs. Vinkius wraps the entire MCP data transit in a zero-trust architecture, ensuring that your customer purchase records remain completely encrypted and inaccessible to external nodes.

Coordinate teams of autonomous retail agents to manage NCR Voyix stores and inventory using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NCR Voyix MCP to CrewAI

Create your Vinkius account to connect NCR Voyix 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 NCR Voyix with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Store and Inventory Audits

The `list_inventory` tool allows your specialized CrewAI stock-monitoring agent to track shelf levels across multiple retail locations. This agent runs in parallel with a logistics coordinator agent that uses `get_site` to map out physical delivery addresses. Instead of relying on a single bot to do everything, CrewAI divides the labor so one agent flags low stock while another calculates shipping routes. They share memory during the run, making sure your replenishment plans are based on real-time site constraints.

Autonomous Customer Support Escalation

The `list_customers` tool provides your support CrewAI agents with immediate access to buyer profiles and contact records. When a customer raises an issue, a researcher agent pulls their history while a moderator agent checks their active status. By calling `get_loyalty_programs`, the crew can verify if the customer belongs to a premium tier and automatically prioritize their ticket. The entire resolution process happens autonomously, escalating only the most complex disputes to human staff.

CrewAI MCP Server Multi-Agent Order Dispatch

The `list_orders` tool feeds raw purchase transactions directly to a dispatch agent in your CrewAI team. This agent passes individual order IDs to `get_order` to verify that the items are packed and ready for shipment. If an item is missing, the dispatch agent alerts a sourcing agent to query `list_products` and find alternative SKUs. This collaborative loop resolves order discrepancies on the fly without halting your warehouse operations.

Setup guide

Set up NCR Voyix 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 NCR Voyix tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent NCR Voyix 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="NCR Voyix Analyst",
        goal="Access and analyze NCR Voyix data via MCP.",
        backstory="Expert analyst with direct NCR Voyix access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent NCR Voyix 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 NCR Voyix. 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 NCR Voyix 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 NCR Voyix MCP in CrewAI

You pass the Vinkius URL directly in the `mcps` array of your CrewAI configuration to share the MCP Server. This allows your inventory agent to call `list_inventory` while your sales agent simultaneously calls `list_orders` within the same execution loop.

Yes, you can use `MCPServerHTTP` with a `tool_filter` to limit tool exposure. This ensures your customer support agent can only access `list_customers` while your warehouse agent is restricted to `list_inventory` and `get_site`.

The framework supports stdio, SSE, and Streamable HTTP transports out of the box. This flexibility allows your multi-agent crews to run locally during development or deploy to cloud-hosted environments for continuous production tracking.

CrewAI coordinates agents sequentially or hierarchically, managing concurrent calls to endpoints like `list_products` and `list_catalogs` in the background. The manager agent coordinates the output, preventing race conditions when multiple agents query the same catalog.

All transaction details retrieved via `get_order` are processed in ephemeral memory and never written to persistent logs. Vinkius wraps the entire MCP data transit in a zero-trust architecture, ensuring that your customer purchase records remain completely encrypted and inaccessible to external nodes.

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