
Bench
io.github.seayniclabsPublished by GitHub account seayniclabsv0.4.3Updated Oct 30, 2026
USB hardware discovery for AI tools: find maker boards, serial ports and chips.
Overview
Native macOS MCP server that lets an AI assistant discover USB maker boards, identify chips, read and write serial ports, and flash firmware with approval.
- What you can do
- Discover and inspect USB devices: enumerate devices, identify boards, read descriptors, hub topology, power info, events and snapshots
- Work with serial ports: list, open, read, write, write-and-expect, monitor and close them
- Flash and probe firmware: detect the chip type and flash with esptool, dfu-util, avrdude or UF2
- Send and read raw HID reports, and decode ESP32 or ARM crash dumps into source lines
- Manage devices: reset a port, eject a device, tag devices, and run diagnostics
- Serve built-in skill prompts and resources for bring-up, serial debugging, safe flashing and systematic debugging
- When to use it
- Useful for developers on a Mac who work with Arduino, ESP32, Raspberry Pi Pico or similar boards plugged in, and want the assistant to name the board, find its port, debug serial output or crashes, and flash firmware.
- Requirements
- Local macOS 14 or later machine (Apple Silicon or Intel); Linux is not supported in this release. Install via the MCP Bundle, Homebrew (needs Xcode 16.3 or later), a pinned source build, or the Claude Code plugin. Firmware flashing needs esptool, dfu-util, avrdude or UF2 installed; crash decoding uses addr2line. Optional environment variables such as BENCH_MODULES, BENCH_DEBUG_ENABLED, BENCH_APPROVE_DEVICE_WRITES, BENCH_APPROVAL_LOG, BENCH_ADDR2LINE and BENCH_SKILLS_DIR configure it. No…
Installation
In SourceWeft
- Open Bench in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Bench
Made by Seaynic Labs. Need tools like this built around your own systems? We do that.
USB hardware discovery for your AI tools.
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.
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?"
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.
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.
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.
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:
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
The 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:
The 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:
Connect your AI client
Bench speaks plain MCP over stdio. Use the full path to the binary in each snippet.
Claude Code
Claude Desktop (claude_desktop_config.json)
Cursor (~/.cursor/mcp.json)
VS Code (.vscode/mcp.json)
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.
Build and test
Bench 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:
After 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.
Source: README.md at commit fa81668
Tools
0Version history
1- v0.4.3LatestOct 29, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts