How to Use the myDevices MCP in CrewAI

Q: How do I assign different myDevices tools to different CrewAI agents?

Use the toolfilter option when defining the MCPServerHTTP tool for each agent. This lets you give a "Monitor" agent access to getsensordata while a "Commander" agent only gets sendcommand.

Q: Can I build a CrewAI team where one agent monitors myDevices and another acts?

Yes, that's a primary use case. One agent polls listalerts or getsensordata. When it finds an issue, it delegates a task with the relevant device ID to another agent that has the sendcommand tool.

Q: How would a CrewAI agent get historical data from myDevices to diagnose a problem?

The agent would use the getsensorhistory tool. You can configure it to fetch the last hour or day of data for a specific sensor to understand the context of an alert.

Q: Is it possible for my CrewAI agents to see all sensors on a specific myDevices device?

Definitely. First, get the device ID using listdevices. Then, an agent can call listsensors with that ID to get a complete list of available sensors on that piece of hardware.

Deploy an autonomous crew with CrewAI to manage your myDevices fleet via this MCP Server. Agents can monitor, diagnose, and act on IoT data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect myDevices MCP to CrewAI

Create your Vinkius account to connect myDevices 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 myDevices with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Monitoring & Response

Assign roles to your agents. A "Monitor" agent can run in a loop, constantly calling `get_sensor_data` on critical devices. A "Responder" agent sits idle, waiting for the Monitor to delegate a task. When the Monitor agent detects an anomaly, it passes the device ID and sensor data to the Responder. The Responder then takes over, using `send_command` to issue a corrective action, like turning on a cooling system. It's a fully autonomous feedback loop.

Automated Diagnostics and Reporting

Set up a "Triage" agent to watch the `list_alerts` feed. When a new alert comes in, it delegates the investigation to a "Diagnostic" agent. The Diagnostic agent gets to work. It uses `get_device` to get context, pulls `get_sensor_history` to find the root cause, and then formats a report. This entire MCP toolset supports that workflow.

Manage Your Fleet with a CrewAI Team

Divide and conquer fleet management. An "Auditor" agent can periodically run `list_applications` and `list_devices` to create a full inventory of your assets. It can then delegate tasks to a "Configurator" agent. For example, if a device is missing a specific tag, the Auditor tells the Configurator which device to update. The agents work together, using shared context to manage the entire myDevices environment.

Setup guide

Set up myDevices 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 myDevices tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Use the `tool_filter` option when defining the `MCPServerHTTP` tool for each agent. This lets you give a "Monitor" agent access to `get_sensor_data` while a "Commander" agent only gets `send_command`.

Yes, that's a primary use case. One agent polls `list_alerts` or `get_sensor_data`. When it finds an issue, it delegates a task with the relevant device ID to another agent that has the `send_command` tool.

The agent would use the `get_sensor_history` tool. You can configure it to fetch the last hour or day of data for a specific sensor to understand the context of an alert.

Definitely. First, get the device ID using `list_devices`. Then, an agent can call `list_sensors` with that ID to get a complete list of available sensors on that piece of hardware.

Your CrewAI instance only needs the Vinkius MCP URL. Vinkius manages the myDevices authentication securely. Every request for your IoT sensor data and device commands is executed in a separate, zero-trust environment that's destroyed after the call completes.

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