"A tool or device for scraping data or materials" matching MCP servers:

Enables a Dot to publish short chat summaries and multiple-choice questions to an ESP32 touchscreen, read persisted touch answers, record receipts, and inspect status through Secure MCP Tunnel.

Enables AI agents to perceive and quantitatively verify physical hardware through USB webcams and RTSP/HTTP network streams, returning inline image content plus numerical metrics such as brightness, contrast, edge density, motion, SSIM baseline comparisons, and OCR text. Agents can watch feeds for visual conditions, correlate buffered frames with serial/log/MQTT events, and apply privacy masks and access controls.

Enables AI clients to compile and upload Arduino sketches, manage boards, cores, and libraries via arduino-cli, scaffold projects, and read serial output over stdio.

Runs a Model Context Protocol server directly on Axis cameras, enabling any MCP-capable AI to inspect and control the camera without cloud or middleware.

Enables AI assistants to interact with physical serial port devices across platforms (Windows COM/Linux tty) with support for asynchronous communication, URC pattern recognition, and structured logging.

Enables LLMs to interact with embedded devices by reading and writing Segger RTT data through a J-Link debugger.

Enables AI agents to search a catalog of MCP servers for physical hardware such as ESP32, Arduino, Raspberry Pi, 3D printers, Home Assistant devices, cameras, Zigbee and lab gear, returning install commands and ready-to-paste client configs. It also supports browsing device families and getting ranked recommendations for a specific device or model.

Local or self hosted LLM server for Labgrid hardware-in-the-loop device operations

MCP server for running shell commands on a Linux development board via UART serial.

Enables MCP clients to capture digital waveforms from an ALIENTEK USB logic analyzer, run 208 sigrok protocol decoders with stacked chains (like I2C→SSD1306 or UART→Modbus), and analyze or write .atkdl waveform archives offline without the device attached.

Exposes 238 schema-typed tools over streamable-HTTP MCP that let a client drive a Flipper Zero, an AWOK Biscuit (ESP32-C5) and an ESP32 Marauder — scanning, screen mirroring, storage, and other device operations — from natural-language or direct tool calls. Transmit/attack tools stay behind an explicit human confirmation gate.

MCP server that lets AI agents configure the EDU09 USB oscilloscope, acquire and measure waveforms, and export them over stdio or streamable HTTP. It can run against real hardware, a built-in simulator, or bridge to a GUI that already owns the device.

Enables users to manage Android ROM projects through MCP by importing, unpacking, repacking, and synthesizing images, DAT/BR files, and super partitions using the toolkit’s shared workflows.

Enables agents to discover devices, query their capabilities, invoke system calls, and stage resources or deliver apps to connected WishOS hardware through a self-hosted connector and relay. It routes device-initiated tasks into an existing harness session (Codex, Claude Code, and others), keeping inference, tools, and history with that agent while handling voice, interface, and app transfer to the device.

Bridges a RisalDash ESP32/ESP8266 device to MCP — every dashboard widget becomes a get_/set_ tool, so an agent can read sensors and toggle relays.

Exposes a single tool run_bash for executing arbitrary shell commands on a Raspberry Pi or host, with no security restrictions, using LangChain and Streamable HTTP transport.

An MCP server for source-grounded, page-cited evidence retrieval tailored for embedded and firmware development, returning verbatim snippets with exact citations or 'no match' to prevent fabrications.

Enables AI agents to control serial port devices (modems, instruments, embedded boards) via MCP tools for listing ports, connecting, and sending/receiving commands.

MCP server that lets LLMs talk to serial devices: microcontrollers, routers, modems, embedded Linux, anything with a UART.

Lets AI assistants read, command, and debug microcontrollers over a serial connection via MCP. Provides tools for serial port discovery, reading serial output, sending commands, and decoding register values.