Bench
Enables identification, monitoring, and interaction with Adafruit USB devices and maker boards. Provides tools for device discovery, serial port mapping, firmware flashing, and HID communication with Adafruit hardware.
Provides comprehensive support for Arduino boards including automatic device recognition, serial port detection (/dev/cu.* mapping), firmware flashing via avrdude, and bidirectional serial communication for debugging and programming.
Recognizes Raspberry Pi devices connected via USB and provides detailed device information, serial port enumeration, and system integration for USB-based communication with Raspberry Pi hardware.
Identifies SparkFun development boards and USB devices with support for automatic classification, serial communication, firmware flashing, and event monitoring for connected SparkFun hardware.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Made by Seaynic Labs. Need tools like this built around your own systems? We do that.
Bench is a native macOS MCP server for developers who work with boards plugged into their Mac: Arduino, ESP32, Raspberry Pi Pico and other USB boards. It names the board, finds its serial port, reads and writes that port, detects the chip, decodes crash dumps, and flashes firmware with your approval. Bench is free and open source, made by Seaynic Labs.
Security card | |
Network | None. Bench makes no network calls and sends no telemetry. |
Files | Reads the skills folder beside the binary. Writes the approval log ( |
Secrets | Bench stores no credentials and needs none. Its settings are environment variables only, and it never returns them to the model. |
Read-only tools | 13: |
Needs your approval | 7: |
Changes without approval |
|
Startup cost | about 6,000 tokens (24 tools, 5 skill prompts) |
Changes | Tool and prompt text is locked by hash ( |
First five minutes
Install it:
brew install seayniclabs/tap/bench(see Install).Run
bench --doctor. It prints one line per check and aFIXline for each problem.Connect your AI client (see Connect your AI client).
Ask it to call
bench_modules. It lists the modules that are on and their tools.Plug in a board and ask: "Which boards are connected, and which serial port is each one on?"
Related MCP server: sahara-mcp
Audience and modules
Bench is for developers working with connected hardware. It is one server made of modules. You switch modules on or off. Every module that shipped before 0.4.0 is on by default. A module added in a later release ships off, so you choose to turn it on.
Module | Status | What it does |
| Ready (always on) | Health check and module discovery |
| Ready | Enumerate, identify and inspect USB devices; hub tree; power; events; snapshots; port reset; eject |
| Ready | List serial ports; open, read, write, write-and-expect, monitor and close them |
| Ready (needs the flashing tool installed) | Detect chip type; flash with esptool, dfu-util, avrdude or UF2 |
| Ready | Send and read raw HID reports |
| Ready, off by default (new in 0.4.0) | Decode ESP32 Guru Meditation and ARM HardFault dumps into source lines with addr2line |
Linux is not in this release. It is planned behind the same tools.
Skills
Skills are short, tested guides for the jobs Bench does. Any app that speaks MCP gets them as prompts (one per skill) and resources (every file in the skill). Apps that read Agent Skills directly load the same skills/ folder.
Skill | Use it for |
| Setting up Bench, switching modules, reading approvals and errors |
| Taking a new board from USB to a working serial round trip |
| Garbled, silent, looping or unresponsive serial output, and crash dumps |
| Flashing firmware: checking the target and the file, then the approved write |
| Finding the cause of a bug before changing code (credited, see CREDITS.md) |
Tools
25 tools in total. 24 are on by default; decode_crash needs the debug module.
core: ping, bench_modules
usb: list_usb_devices, get_device_info, identify_device, eject_device, hub_topology, tag_device, port_reset, power_info, monitor_events, snapshot_state, diagnose_device, device_descriptors
serial: list_serial_ports, serial_open, serial_read, serial_write, serial_write_and_expect, serial_close, serial_monitor
firmware: chip_detect, flash_firmware
hid: hid_send
debug: decode_crash
Call bench_modules first to see what is on and how to change it.
Settings
All settings are environment variables. Bench starts with an empty environment, and a tool call tells you which variable is missing.
Variable | Default | Effect |
| the defaults | Comma list of modules to enable, for example |
| per module |
|
| off |
|
|
| Where the approval log is written. |
| found on PATH | Full path to the addr2line that |
| found next to the binary | Folder of skills to serve, when it is not beside the binary. |
Safety
Bench can change hardware, so some calls are gated.
Device writes need approval.
serial_write,serial_write_and_expect,flash_firmware,port_reset,eject_device,chip_detect(it resets the chip into its bootloader), andhid_sendwith an action other thanget_reportorlist_reportschange a device or its state. Your client asks you through its approval prompt, and the prompt shows the full arguments. A flag from the model, such asconfirm: true, does not count as approval.Clients that cannot show a prompt are refused. Set
BENCH_APPROVE_DEVICE_WRITES=1in the server's environment to allow writes without a prompt. Only do this when you trust every tool call your AI client makes.Every approval is logged. Each request, grant, decline and refusal goes to the approval log. Payloads and file contents are not written there.
Reads are not gated. Discovery, monitoring, serial reads and
serial_monitor,diagnose_device, and crash decoding run without a prompt.Local only. Bench makes no network calls and needs no root. Serial access on Linux (future) will need the
dialoutgroup, not sudo.
See SECURITY.md for the reporting policy and the list of what Bench touches.
Errors
Every error reads bench.<module>.<code>: <message> Fix: <hint>, for example:
bench.serial.write_not_approved: serial_write changes a device and no approval was given. ... Fix: Set BENCH_APPROVE_DEVICE_WRITES=1 in the server's environment and restart it, or use a client that supports MCP elicitation.Every tool result also has structuredContent with ok, module, tool and text.
Install
Claude Desktop (MCP Bundle)
Download bench-<version>-darwin-universal.mcpb from the latest release and open it: Claude Desktop shows the install dialog. The bundle carries the binary (Apple Silicon and Intel, macOS 14 or later) and the skills, so it needs neither Homebrew nor Xcode. The binary is ad-hoc signed, not notarized. Check the download against the .sha256 file next to it in the release.
Homebrew
brew install seayniclabs/tap/bench
bench --doctorThe formula builds from source with Swift, so it needs Xcode 16.3 or later. It installs the binary as bench and the skills to share/bench/skills, next to it.
Pinned install
Use this when you want exactly the 0.4.3 source, not whatever the formula points at:
git clone --branch v0.4.3 https://github.com/seayniclabs/bench.git
cd bench
swift build -c release
codesign --force --sign - --entitlements Sources/Bench/Bench.entitlements .build/release/Bench
.build/release/Bench --doctorThe skills are read from skills/ in the checkout, because the build directory sits inside it.
Claude Code plugin
The repository also packages Bench as a Claude Code plugin (.claude-plugin/plugin.json and .mcp.json): the server and its skills in one install. The plugin runs the bench binary from your PATH, so install Bench with Homebrew first. Then add the Seaynic Labs marketplace and install the plugin:
/plugin marketplace add seayniclabs/plugins
/plugin install bench@seayniclabsConnect your AI client
Bench speaks plain MCP over stdio. Use the full path to the binary in each snippet.
Claude Code
claude mcp add bench -- $(which bench)Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"bench": {
"command": "/absolute/path/to/bench",
"args": []
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"bench": {
"command": "/absolute/path/to/bench",
"args": []
}
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"bench": {
"type": "stdio",
"command": "/absolute/path/to/bench",
"args": []
}
}
}To set a variable, add an env object next to args, for example "env": { "BENCH_DEBUG_ENABLED": "1" }.
Try these
"Which boards are connected to this Mac, and which serial port is each one on?"
"Identify the board on /dev/cu.usbserial-2120 and tell me its exact chip."
"Bring up my ESP32: confirm the chip, read its boot output, and check it answers
ping.""My ESP32 keeps rebooting. Decode the crash in this log against
build/firmware.elf.""Flash
build/firmware.binonto the board with serial number ABC123. Ask me to approve it first."
How it works
Bench uses Apple's IOKit framework to enumerate USB devices. It adds serial port detection (/dev/cu.*), storage details from diskutil, and a built-in database of known maker boards. It talks to your AI tool over stdio using the Model Context Protocol.
AI client --stdio/JSON-RPC--> Bench --IOKit--> USB device tree
--diskutil--> storage info
--/dev/cu.*--> serial ports
--device DB--> board recognition
--addr2line--> crash decoding (debug module)Build and test
swift build # debug build
swift build -c release # release build
swift test # unit tests and stdio testsBench requires Swift 6.1 or later and targets macOS 14 or later. The tests start the built binary with an empty environment, so run swift build before swift test if you change the server.
The checks that CI and release runs use:
python3 scripts/check_skills.py # every skill has license, source and credit; no site links in bodies
python3 scripts/tool_lock.py --check # tool, prompt and instruction text matches the lock
python3 scripts/security_card.py --check # the security card above is current
python3 scripts/mcpb_manifest.py --check # manifest.json lists the tools and prompts the binary serves
scripts/pack_mcpb.sh .build/release/Bench dist # pack the MCP Bundle and check it unpacked
python3 scripts/scan_identifiers.py . # no private identifiers in the treeAfter you change a tool, prompt or the instructions, run python3 scripts/tool_lock.py and python3 scripts/mcpb_manifest.py, and add a changelog line in the same change. After you change the card's inputs, run python3 scripts/security_card.py and paste its output between the card markers.
Changelog
See CHANGELOG.md.
License
MIT. Published by Seaynic Labs. Third-party material is listed in CREDITS.md.
Built by Seaynic Labs. We build tools like this around a business's own systems: local-first, with a person approving every change. See custom integrations.
This server cannot be deployed
Maintenance
Related MCP Connectors
Find public MCP tools and SDKs. Compact setup and Sample cards. Free discovery needs no key.
Generate IDs, QR codes, and hashes, encode values, geolocate IPs, plus gated host diagnostics.
Developer toolkit: UUID, timestamp, unit conversion, JSON tools, and QR code (SVG). Free.
Run, build, and validate firmware on virtual hardware from your AI agent. Hardware knowledge corpus.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables control of Digilent WaveForms instruments (oscilloscope, AWG, logic analyzer) over USB, supporting devices like Analog Discovery 2/3 and Digital Discovery.3MIT
- AlicenseNot gradedqualityCmaintenanceEnables LLM agents to interact directly with Qualcomm EDL devices over USB, including device enumeration, Sahara protocol handshake, SoC identity queries, Firehose programmer upload, command-mode execution, and device reset.GPL 3.0
- AlicenseAqualityCmaintenanceEnables AI agents to communicate with serial devices such as Arduinos, ESP32s, USB-UART adapters, and RS-232 instruments by discovering ports, opening connections, sending commands, reading responses, and controlling reset lines.121MIT
- AlicenseAqualityAmaintenanceLocal serial and USB hardware access for coding agents, with typed YAML protocol commands, checksum validation, audited writes, lossless captures, hardware-free replay, and MCP App visualizations. Runs locally over stdio; live hardware use requires a serial device connected to the same machine.187MIT