Bench

Bench

USB hardware discovery, device identification, serial communication, and diagnostics for makers and hardware engineers.

Category
Visit Server

README

<p align="center"> <img src="docs/assets/bench-logo.svg" alt="Bench" width="200"> </p>

<h1 align="center">Bench</h1>

<p align="center"><strong>USB hardware discovery for your AI tools.</strong></p>

Bench is a native macOS MCP server that gives AI tools like Claude Code, Cursor, and Windsurf visibility into connected USB hardware. It identifies devices, finds serial ports, and recognizes common maker boards — so your AI assistant knows what's on your bench.

No API keys. No drivers. One command to install.

What it does

22 tools across four categories:

Discovery

Tool Description
ping Health check — returns server status, version, macOS version
list_usb_devices List all connected USB devices with vendor, type, speed, serial
get_device_info Detailed info on a specific device by serial, location ID, or name
identify_device Smart identification of 83+ known maker/dev boards
list_serial_ports Enumerate serial ports with USB device matching
hub_topology USB hub tree view showing port hierarchy and connections
device_descriptors Full USB descriptor chain — interfaces, endpoints, class codes
chip_detect Detect exact chip type of ESP32/microcontroller via esptool

Monitoring

Tool Description
monitor_events Detect USB connect/disconnect events between calls
snapshot_state Capture and diff USB device state snapshots
diagnose_device Query system logs for USB errors on a specific device
power_info Per-device power draw, bus budgets, charging detection

Management

Tool Description
eject_device Safely unmount and eject removable storage
tag_device Persistent user-defined aliases for devices
port_reset Reset a USB port to recover frozen devices
flash_firmware Flash firmware via esptool/dfu-util/avrdude/UF2
hid_send Send/receive raw HID reports

Serial Communication

Tool Description
serial_open Open a serial connection with configurable baud rate, data bits, parity
serial_read Read available data from an open serial connection
serial_write Write data or commands to an open serial connection
serial_close Close an open serial connection
serial_monitor Capture serial output for N seconds (boot logs, debug output)

Features

  • Device classification — automatically categorizes devices as storage, input, hub, video, serial adapter, microcontroller, or debugger
  • Serial port detection — maps USB devices to their /dev/cu.* serial ports (the #1 question makers ask)
  • 83+ known boards — recognizes Arduino, Raspberry Pi, ESP32, Adafruit, SparkFun, Teensy, STM32, and common USB-serial chips
  • Storage info — mount points, capacity, and free space for USB drives
  • USB monitoring — event tracking, state snapshots, diagnostic log queries, and power analysis
  • Firmware flashing — flash ESP32, STM32, Arduino AVR, and RP2040 boards directly
  • HID interaction — send and receive reports from Stream Decks, macro pads, and custom HID devices
  • Serial communication — open, read, write, and monitor serial ports with configurable baud rate, data bits, parity, and stop bits

Requirements

  • macOS 14+ (Sonoma or later) on Apple Silicon
  • An MCP-compatible AI tool (Claude Code, Cursor, Windsurf, etc.)
  • For building from source: Xcode 16.3+ / Swift 6.1+

Install

Homebrew (recommended)

brew install seayniclabs/tap/bench

From source

git clone https://github.com/seayniclabs/bench.git
cd bench
swift build -c release
codesign --force --sign - --entitlements Sources/Bench/Bench.entitlements .build/release/Bench

The binary is at .build/release/Bench.

Add to Claude Code

claude mcp add bench -- $(which bench)

Or add manually to ~/.claude.json:

{
  "mcpServers": {
    "bench": {
      "command": "/path/to/bench",
      "args": []
    }
  }
}

Usage

Once connected, just talk to your AI tool:

  • "What USB devices are connected?"
  • "What port is my Arduino on?"
  • "Identify the device on /dev/cu.usbserial-2120"
  • "Eject the Samsung T7"
  • "Show me all storage devices"
  • "Open a serial connection to /dev/cu.usbserial-2120 at 9600 baud"
  • "Monitor the serial output from my ESP32 for 10 seconds"

How it works

Bench uses Apple's IOKit framework to enumerate USB devices natively on macOS. It enriches results with serial port detection (/dev/cu.* scanning), storage info (diskutil), and a built-in database of known maker boards. It communicates with AI tools over stdio using the Model Context Protocol (JSON-RPC).

AI Tool  --stdio/JSON-RPC-->  Bench  --IOKit-->  USB Device Tree
                                     --diskutil-->  Storage Info
                                     --/dev/cu.*-->  Serial Ports
                                     --DeviceDB-->  Board Recognition

No special permissions needed. IOKit USB enumeration works without entitlements from a CLI binary.

Building

swift build             # debug build
swift build -c release  # release build
swift test              # run tests

Bench requires Swift 6.1+ and targets macOS 14+.

License

MIT

Credits

Built by Seaynic Labs.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured