Iris
This MCP server enables AI agents to read MQTT and Sparkplug B data via tools like list_topics, get_latest, and read_all, providing read-only access to latest sensor values.
README
Iris
An MQTT / Sparkplug B bridge for the OT stack. Iris subscribes to a broker, keeps the latest value per topic, exposes them over REST and as MCP tools for AI agents, and can forward every reading to a Clio historian.
Named for Iris, messenger of the gods — fitting for a message-bus bridge. It mirrors the ModBridge shape (CLI + REST + MCP) for the pub/sub world.
Status
Scaffold with a working MQTT ingest loop. Plain MQTT payloads (numbers, JSON
{"value": ...}, text) are parsed today. Sparkplug B topics (spBv1.0/...)
are detected and flagged; full protobuf payload decoding (via the Tahu schema)
is the next step.
Run
pip install -r requirements.txt
# Subscribe and forward to Clio:
python -m iris subscribe --broker localhost --topic 'plant/#' --clio http://localhost:8010
# Bridge + REST API:
python -m iris serve --broker localhost --topic '#' --api-port 8011
# MCP server (owns its own subscription, exposes read tools to agents):
python -m iris.mcp_server
Configuration via flags, env (IRIS_BROKER_HOST, IRIS_BROKER_PORT,
IRIS_TOPICS, IRIS_CLIO_URL, IRIS_SOURCE), or config.example.toml.
REST API
| Method | Path | Purpose |
|---|---|---|
| GET | /health |
Liveness + topic count |
| GET | /topics |
Topics seen since connect |
| GET | /latest |
Latest sample for a topic |
| GET | /values |
Latest sample for every topic |
MCP tools (read-only)
list_topics, get_latest(topic), read_all. Publishing back to the broker is
a write path and is intentionally not exposed — consistent with the
disabled-by-default posture on writes elsewhere in the stack.
Tests
pytest
License
MIT © AddisonTech
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.