Explore
MCP servers and skills: search, filter by where they run, and compare.
Mobile-Test-MCPchoumine
Local
MCP servers and skills: search, filter by where they run, and compare.
An LLM-Powered UI Test Automation Framework for Android
PythonMIT★ 2Few starsNo key
MCP server for profiling Apple platform apps with xctrace/Instruments
PythonMIT★ 3Few starsNo key
PythonMIT★ 4Few starsNo key
PythonMIT★ 2Few starsNo key
Voxel — Pocket AI companion. Animated cube mascot on Pi Zero 2W + Whisplay HAT, connected to your AI agent team via OpenClaw.
PythonMIT★ 4Few starsNo key
Evidence-first Android and iOS security audits with CLI, TUI, MCP, public vulnerability intelligence, and OWASP-aligned evidence.
PythonMITFew starsNo key
An open-source control plane that gives Codex and other MCP agents hands on a real iPhone.
PythonGPL-3.0★ 2Few starsNo key
MCP server that lets AI agents drive a physical iPhone through macOS iPhone Mirroring.
PythonMITFew starsNo key
Device Context Protocol — bridge LLM agents to physical devices. Sub-50-byte frames, 27.6KB flash / 0.6KB RAM measured on ESP32, capability-scoped and safe by design. Complementary to MCP. Paper: arXi
PythonMIT★ 62No key
A framework that connects AI assistants to physical devices - sensors, actuators, cameras, and edge ML boards via MCP
PythonApache-2.0★ 4Few starsNo key
Open Model Hardware Protocol: an MCP-style open protocol for AI agents to find, understand and safely operate lab and factory hardware
PythonApache-2.0★ 3Few starsNo key
Agent-driven design studio for ESPHome-compatible (e.g. ESP32/ESP8266, RP2040) + LoRaWAN devices: generates ESPHome YAML, KiCad schematic/PCB, 3D-printable enclosures, and builds/flashes/provisions Lo
PythonMIT★ 26No key
Local daemon that turns Claude Code / Codex lifecycle events (permission prompt, waiting for input, turn done) into haptic feedback on physical devices: DualSense, OpenShock, Lovense. Hooks first, MCP
PythonMIT★ 2Few starsNo key
ClawTouch MCP server — exposes a real USB-HID keyboard/mouse (Raspberry Pi Pico 2) as Model Context Protocol tools for any LLM agent. MIT.
PythonMIT★ 13No key
An automated IoT fleet deployment reliability reviewer built on a researched failure-mode taxonomy, locked severity rubric, and 100-case evaluation corpus.
SkillMIT★ 2Few starsNo key
A pre-registered, reproducible benchmark of agent-operated mobile-device tooling: 4 MCP tool stacks, 1 confined agent, 10 frozen tasks, 2 full grids, every transcript published — including the ones we
PythonMITFew starsNo key
Open Model Hardware Standard - AI agent hardware control
PythonMIT★ 1Few starsNo key
Run iOS Simulator goals with Jev, compare decision models, and replay every attempt. Python CLI and Brigade host wrapper.
SkillMIT★ 4Few starsNo key
iOS-first computer-use runtime that drives a real iPhone from screen observations: frame capture, OCR/VLM perception, action, verification, and screen memory behind pluggable seams (PicoKVM/noop/stati
SkillMIT★ 8No key
FastMCP 3.2 server for AI agents to issue verbal commands to Alexa devices
PythonMIT★ 1Few starsNo key
Glinx is a Python middleware framework that connects physical hardware to AI agents without custom adapter code. It ingests sensor data from any protocol, enriches it with semantic meaning, and expose
PythonMIT★ 3Few starsNo key
openclaw / openfang inspired experiment. adds mcp server fleet and robotics
PythonMIT★ 4Few starsNo key
Who stands behind it
