MCP-Edge
Integration with Arduino devices and Arduino IoT Cloud, enabling management of device properties and firmware-in-the-loop testing with Arduino, ESP32, and RP2040 boards.
Exposes Edge Impulse ML inference as MCP tools, allowing AI agents to run models on edge devices.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP-Edgeread temperature from bedroom sensor"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP-Edge
Extend the Model Context Protocol (MCP) to edge and IoT devices.
MCP-Edge lets cloud LLM agents discover and invoke physical hardware through the same tool interface they already use for software APIs. It provides:
a gateway that bridges cloud-native MCP transports (SSE / HTTP) to constrained device channels (UART, BLE, local Wi-Fi), presenting every downstream device as a standard MCP tool provider;
MCP-Lite, a lightweight MCP server for devices with as little as ~512 KB of RAM;
a four-tier device taxonomy (constrained MCUs, smart IoT nodes, BLE-only wearables, Linux-class edge computers) that maps an MCP strategy to each tier;
protocol adaptations for constrained links: CBOR encoding, schema caching, connection pooling, and offline request buffering.
Status: alpha, under active development. The public API is unstable and will change. This repository is a reference implementation of the framework described in the MCP-Edge paper (IEEE Cloud Summit 2026). Performance figures reported in the paper are projected estimates, not measurements taken from this codebase.
Installation
Requires Python 3.10+. Not yet published to PyPI — install from source:
pip install -e ".[dev]"Optional transport backends:
pip install "mcp-edge[serial]" # UART / USB serial devices
pip install "mcp-edge[ble]" # BLE devices
pip install "mcp-edge[wifi]" # local Wi-Fi / mDNS discoveryRelated MCP server: mcp2tcp
Quickstart
Coming soon — the gateway and device simulator land in upcoming releases.
Roadmap
v0.1 — gateway core, serial + simulated transports, protocol adaptations, device simulator, CLI, hermetic CI
v0.1–0.2 — Wokwi firmware-in-the-loop tests (Arduino / ESP32 / RP2040)
v0.2+ — Edge Impulse (inference as an MCP tool) and Arduino IoT Cloud (properties as MCP) integration examples; Renode / QEMU backends
Development
python -m venv .venv
.\.venv\Scripts\Activate.ps1 # PowerShell (Windows); use `source .venv/bin/activate` on Unix
pip install -e ".[dev]"
pytest -q
ruff check .License
MIT — see LICENSE.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jemsbhai/mcp-edge'
If you have feedback or need assistance with the MCP directory API, please join our Discord server