How to Use the myDevices MCP in LlamaIndex

Q: How do I ingest myDevices sensor history into a LlamaIndex vector store?

You call getsensorhistory to pull raw time-series data, then convert those JSON records into Document objects. LlamaIndex indexes these documents, allowing you to run semantic search queries over past telemetry patterns.

Q: Can a LlamaIndex agent query multiple myDevices applications?

Yes, the agent uses listapplications to discover distinct environments, then creates separate index namespaces for each. This keeps telemetry from your agricultural setup separate from your industrial machinery index.

Q: Can I filter which myDevices tools are available to the index?

Yes, you can use the allowedtools filter during setup to restrict your RAG pipeline. For example, you can expose listsensors for querying while blocking sendcommand to prevent accidental hardware modifications.

Index live Cayenne IoT telemetry into LlamaIndex vector stores to query real-time hardware states using natural language.

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 LlamaIndex

Create your Vinkius account to connect myDevices to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index raw IoT telemetry with this LlamaIndex integration

The `get_sensor_history` tool feeds raw Cayenne historical logs directly into your LlamaIndex document store using this MCP Server. Your LlamaIndex agent queries this indexed data to find anomalous patterns across thousands of past data points without parsing massive CSV files manually. By combining historical logs with live inputs from `get_sensor_data`, the system grounds its answers in actual hardware performance. This eliminates hallucinated status reports and ensures your team gets accurate, data-backed diagnoses.

Build a queryable knowledge base of myDevices hardware

Using `list_devices` and `list_sensors`, LlamaIndex builds a structured index of your entire physical hardware footprint. The LlamaIndex agent searches this index to map which sensors belong to which physical assets, resolving natural language queries like 'find the temperature sensor on boiler 4'. This semantic mapping connects raw hardware addresses to human-readable locations. When a technician asks for a status update, the agent uses `get_device` to fetch the exact node details and translates the technical payload into a clear summary.

Trigger actions from RAG search results

The `send_command` tool allows your LlamaIndex RAG application to act on the insights it retrieves from your knowledge base. When the LlamaIndex agent detects an active warning via `list_alerts` and matches it to a known troubleshooting guide in your vector store, it executes the recovery command automatically. This bridges the gap between passive document search and physical operations. Your agent doesn't just tell you how to fix a failing cooling loop—it sends the actual signal to turn the fan on.

Setup guide

Set up myDevices MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all myDevices MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to myDevices tools.",
)
response = await agent.run("List recent myDevices data")

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 LlamaIndex

You call `get_sensor_history` to pull raw time-series data, then convert those JSON records into Document objects. LlamaIndex indexes these documents, allowing you to run semantic search queries over past telemetry patterns.

Yes, the agent uses `list_applications` to discover distinct environments, then creates separate index namespaces for each. This keeps telemetry from your agricultural setup separate from your industrial machinery index.

You configure the agent to bypass the vector cache and call `get_sensor_data` directly for real-time queries. Use the index for structural metadata like device locations, but fetch active telemetry live from the Cayenne hardware.

Yes, you can use the allowed_tools filter during setup to restrict your RAG pipeline. For example, you can expose `list_sensors` for querying while blocking `send_command` to prevent accidental hardware modifications.

All raw IoT telemetry and sensor logs fetched via this MCP Server remain in your local runtime or designated vector database. Vinkius processes the Cayenne API requests in an ephemeral sandbox, ensuring your industrial telemetry never leaks to external servers.

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