Neura Market
embedible.io logo

embedible.io

Free

AI that transforms your electronics ideas into working projects.

FreeFree tier
Type
Open Source
Visit Website GitHub (38 stars)

About embedible.io

Embedible is a hosted infrastructure layer for hobbyist hardware that connects devices like Raspberry Pi Pico W or ESP32 to any MCP-compatible AI client (Claude Code, Cursor, etc.) over a secure MQTT-over-mTLS connection. It provides a browser-based provisioning flow, a wiring-diagram editor, and a live dashboard. Users can ask their AI to flash firmware, read sensors, blink LEDs, log temperature, move servos, and more. No CLI tools or router setup required — provisioning is point-and-click. Embedible supports the Model Context Protocol (MCP) over Streamable HTTP transport, turning every owned device into a tool the AI can call (list_devices, push_code, read_dashboard, tail_logs, get_wiring).

Key Features

Browser-based device provisioning with per-device mTLS certificate
MCP-compatible – works with Claude Code, Cursor, and any MCP client
Secure MQTT-over-mTLS connection via AWS IoT Core
AI callable tools: list_devices, push_code, read_dashboard, tail_logs, get_wiring
Wiring-diagram editor and live dashboard
No CLI tools, shared secrets, or router setup required
Supports Raspberry Pi Pico W, Pico 2 W, ESP32 (WROOM-32, DOIT DevKit V1)

Pros & Cons

Pros
  • Point-and-click provisioning – no embedded development experience needed
  • Secure per-device X.509 certificates with scoped AWS IoT policies
  • Works with popular AI coding agents (Claude Code, etc.) out of the box
  • Free tier available for up to 2 devices with 1-day logs
  • Wiring editor and live dashboard included for manual control
Cons
  • Limited hardware support: only Raspberry Pi Pico W, Pico 2 W, and ESP32 variants currently
  • ESP8266 not supported due to insufficient SRAM for AWS IoT TLS handshake
  • Free tier limited to 2 devices and 1-day log retention
  • Requires internet connection and dependency on MCP protocol adoption

Best For

Control hardware (LEDs, servos, sensors) from any AI chat interfaceFlash firmware and read sensor data via natural language commandsBuild prototypes and advanced systems with AI-generated MicroPython codeLog temperature, blink LEDs, move servos using MCP-connected AI agents

FAQ

What is Embedible?
Embedible is a hosted infrastructure layer for hobbyist hardware. It hands your devices to any MCP-compatible AI client (Claude Code, Cursor, etc.) over a secure MQTT-over-mTLS connection, plus gives you a browser-based provisioning flow, a wiring-diagram editor, and a live dashboard. You bring the AI — we handle the device interface.
Which MCP clients can I use?
Any client that speaks the Model Context Protocol over the Streamable HTTP transport. We test against Claude Code; the standard SDK clients work too. You generate an API key in the app, paste a snippet into your client's MCP config, and your devices appear as tools your AI can call.
What hardware is supported?
Raspberry Pi Pico W, Pico 2 W, and ESP32 (WROOM-32, DOIT DevKit V1) are first-class today. ESP32-S3 should work as well. ESP8266 is not supported — its 80 KB SRAM cannot fit the AWS IoT TLS handshake.
How secure is the device connection?
Every device gets its own X.509 certificate, issued during provisioning and stored only on the device (the private key never sits on our servers after handoff). The AWS IoT policy attached to each cert is scoped to that device's own topic prefix, so a compromised device can only talk about itself.
Do I need embedded development experience?
No. Provisioning is point-and-click in the browser, and once a device is online you can ask your AI to write and push MicroPython code, read sensors, and update the dashboard. If you do know embedded, the wiring editor and pin-out tools are there for you.