How to Use the Honeywell Forge MCP in LlamaIndex

Q: How do I integrate Honeywell Forge with LlamaIndex?

Install llama-index-tools-mcp via pip. Set up a BasicMCPClient pointing to your server URL, then convert it using McpToolSpec to get your tool list.

Q: Can LlamaIndex agents acknowledge alarms in Honeywell Forge?

They can. Pass the acknowledgealarm tool to your FunctionAgent. The agent will read the active faults and mark them as reviewed in the audit log.

Q: How do I restrict which tools the agent can use?

Use the allowedtools filter when configuring your MCP setup. You can easily expose read-only metrics like listbuildings while blocking action commands like lockdoor.

Turn your physical buildings into a searchable knowledge base. Connect LlamaIndex to live facility data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Honeywell Forge MCP to LlamaIndex

Create your Vinkius account to connect Honeywell Forge 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 Honeywell Forge with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live building telemetry with LlamaIndex

Static documents only tell half the story. To build a real facility management RAG app, you need live operational data. Your LlamaIndex agent can pull `get_building_details` from the MCP Server and instantly vectorize floor plans, HVAC zones, and operating schedules. When a user asks about the Dallas office, the agent doesn't just read an old PDF. It queries `get_temperature_data` and embeds the current zone conditions directly into the context window. You get answers grounded in reality.

Search historical alarm patterns

Finding recurring faults usually means digging through terrible legacy dashboards. Instead, wire your agent to run `get_alarms` and index the output. It ingests severity levels, timestamps, and fault descriptions into your vector store. Now you just ask your agent why the third-floor HVAC keeps failing. It runs a semantic search across the historical alarm data and cross-references it with `get_energy_usage` metrics. The system spots the correlation between power spikes and compressor warnings automatically.

Map physical security infrastructure

Security audits require exact knowledge of every entry point. You can use the `list_access_points` tool to pull every door, gate, and turnstile into your index. The agent maps the access levels and current `get_door_status` for the entire site. If a guard needs to know which cameras cover the north entrance, the agent queries `list_video_feeds`. It matches the camera locations to the access points and returns the exact RTSP stream URLs. You build a queryable map of your physical security surfaces.

Setup guide

Set up Honeywell Forge 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 Honeywell Forge 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 Honeywell Forge tools.",
)
response = await agent.run("List recent Honeywell Forge 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 Honeywell Forge. 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 Honeywell Forge 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 Honeywell Forge MCP in LlamaIndex

Install `llama-index-tools-mcp` via pip. Set up a `BasicMCPClient` pointing to your server URL, then convert it using `McpToolSpec` to get your tool list.

They can. Pass the `acknowledge_alarm` tool to your `FunctionAgent`. The agent will read the active faults and mark them as reviewed in the audit log.

Only if you embed it into your vector database. If you just pass the MCP tools for live querying, the data remains ephemeral within the agent's memory.

Use the `allowed_tools` filter when configuring your MCP setup. You can easily expose read-only metrics like `list_buildings` while blocking action commands like `lock_door`.

Your infrastructure data remains strictly isolated. When your agent fetches camera stream URLs and locations, the connection authenticates via a single endpoint token. Vinkius manages the ephemeral execution environment to ensure no residual telemetry leaks out.

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