Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Drive a BenchPod hardware-in-the-loop bench: power, flash, UART, I2C, CAN, analog and logic.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
BENCHPOD_CONNECTION, BENCHPOD_LA_VOLTAGE, BENCHPOD_API_KEY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"embeddedci": {
"command": "uvx",
"args": [
"embeddedci-mcp"
],
"env": {
"BENCHPOD_CONNECTION": "your-value",
"BENCHPOD_LA_VOLTAGE": "your-value",
"BENCHPOD_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add embeddedci --env BENCHPOD_CONNECTION=your-value --env BENCHPOD_LA_VOLTAGE=your-value --env BENCHPOD_API_KEY=your-value -- uvx embeddedci-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"embeddedci": {
"command": "uvx",
"args": [
"embeddedci-mcp"
],
"env": {
"BENCHPOD_CONNECTION": "your-value",
"BENCHPOD_LA_VOLTAGE": "your-value",
"BENCHPOD_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"embeddedci": {
"type": "stdio",
"command": "uvx",
"args": [
"embeddedci-mcp"
],
"env": {
"BENCHPOD_CONNECTION": "your-value",
"BENCHPOD_LA_VOLTAGE": "your-value",
"BENCHPOD_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
BENCHPOD_CONNECTION envBENCHPOD_LA_VOLTAGE env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 embeddedci-com 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:BENCHPOD_API_KEY
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(2.13.8)于3天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Python (uv)。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Tools MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Web production tools for AI agents: contrast, JP text, WebP, JSON-LD, slugs, dates and 40+ more
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
An MCP server that lets an AI agent drive an EmbeddedCI BenchPod — a hardware-in-the-loop tester wired to a real board. Ask Claude (or any MCP client) to flash a build, power-cycle the target, watch its UART, pretend to be the sensor it expects, probe its I2C/CAN traffic or drive and measure analog signals, and the pod does it.
It is a thin layer over the embeddedci SDK: every tool maps to SDK calls, so anything an agent discovers interactively can become a pytest test.
uvx), or pip.usb reaches the full API over the pod's USB network adapter (unless Wi-Fi is configured on the pod, which turns USB networking off); status then reports kind usb_net. A serial device path, or usb on older firmware, is the USB console: status, LA voltage and power only, since the STM32 pod's console has no JSON mode. With several pods plugged into one computer, usb errors and lists them by name; pick one with usb: (for example usb:benchpod-baea06).flash: OpenOCD with the cmsis_dap_tcp backend (newer than 0.12.0 — e.g. brew install --HEAD open-ocd, or the xPack build) on the machine running the server. The firmware file is read from that machine too. Flashing a build uploaded to embeddedci.com (build/repo/ref) over a cloud connection needs neither: embeddedci.com runs OpenOCD.claude mcp add benchpod \
-e BENCHPOD_CONNECTION=192.168.1.213 -e BENCHPOD_LA_VOLTAGE=3.3 \ -- uvx embeddedci-mcp
BENCHPOD_LA_VOLTAGE is the board's I/O voltage, configured once here — use 1.8 for a 1V8 board. Without it the agent is told to call set_la_voltage before touching the LA bank.
Both variables are optional. connect picks the pod, first match wins:
connection argument;--connection;BENCHPOD_CONNECTION;benchpod-cli saved with benchpod set-connection (read-only, from ~/.config/benchpod-cli/config.json, or under $XDG_CONFIG_HOME);So the CLI, the SDK and the MCP server share one saved connection. With none of the first four, connect looks for a BenchPod on the LAN over mDNS (like discover) and uses it when it finds exactly one. When it finds none or several, the error lists the pods it heard (name and address) and what to pass instead: host[:port], usb, or embeddedci: for a cloud pod (cloud_list_devices lists those). So claude mcp add benchpod -- uvx embeddedci-mcp is enough for a single pod on your network: just ask the agent to connect.
TLS. A network address uses TLS on port 8443 when the pod has it (firmware 3.9.3+) and pins the pod's certificate on first use, in the same known_pods.json as benchpod-cli; older pods stay on plaintext 8080. BENCHPOD_TLS=on|off and BENCHPOD_TLS_CA work as in the SDK. A changed certificate stops connect with both fingerprints: after a deliberate change, the user runs benchpod lan-tls trust. The lan_tls tool shows the certificate and switches HTTPS-only.
claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):
{
"mcpServers": { "benchpod": { "command": "uvx", "args": ["embeddedci-mcp"], "env": { "BENCHPOD_CONNECTION": "192.168.1.213", "BENCHPOD_LA_VOLTAGE": "3.3" } } } }
The Codex CLI keeps its MCP servers in ~/.codex/config.toml. Add it with the CLI:
codex mcp add benchpod \
--env BENCHPOD_CONNECTION=192.168.1.213 --env BENCHPOD_LA_VOLTAGE=3.3 \ -- uvx embeddedci-mcp
…or write the entry yourself (codex mcp list shows what is configured):
# ~/.codex/config.toml
[mcp_servers.benchpod] command = "uvx" args = ["embeddedci-mcp"] env = { BENCHPOD_CONNECTION = "192.168.1.213", BENCHPOD_LA_VOLTAGE = "3.3" }
Use the device name and an API key — the cloud transport is included:
"env": {
"BENCHPOD_CONNECTION": "embeddedci:my-bench", "BENCHPOD_API_KEY": "eci_…", "BENCHPOD_LA_VOLTAGE": "3.3" }
Or skip the API key: after benchpod login, the server reuses that session (~/.config/benchpod-cli/token.json, refreshed and written back when it has expired) for cloud_list_devices, connect("embeddedci: ") and, on a LAN or USB connection, the pod's stored wiring profile. BENCHPOD_API_KEY wins when set, and inside GitHub Actions the SDK uses OIDC instead.
cloud_list_devices lists the pods on your account and which are online, without connecting to one; pass a result's connection to connect. The session token behind a cloud connection is renewed before it expires, so a long session keeps working.
A cloud pod is shared, so connect takes an exclusive lease (waiting up to --lease-wait seconds if another run holds it). The lease is released by disconnect, or after --idle-timeout seconds without a tool call — the next call reconnects transparently, so an idle chat never blocks CI on that pod.
| Flag | Environment | Default | |
|---|---|---|---|
--connection | BENCHPOD_CONNECTION | the CLI's saved connection, else mDNS | host[:port], serial device, usb, usb: , discover, saved, or embeddedci: ; unset = benchpod set-connection's saved one, else find the one pod on the LAN |
--la-voltage | BENCHPOD_LA_VOLTAGE | — | LA I/O voltage (1.8 or 3.3) applied on connect |
| — | BENCHPOD_API_KEY | — | cloud pods and the waveform library (without it, cloud tools use the benchpod login session) |
| — | BENCHPOD_API_BASE | https://www.embeddedci.com | another embeddedci server |
| — | BENCHPOD_WIRING | — | wiring profile file (.json/.toml) that wins over the stored profile |
| — | BENCHPOD_WIRING_SOURCE | auto | local never asks embeddedci.com for the pod's stored wiring profile |
--lease-wait | — | 30 | cloud: seconds to wait for a busy pod |
--idle-timeout | — | 600 | cloud: release the lease after this many idle seconds (0 = never) |
--timeout | — | 30 | per-command device timeout |
--transport | — | stdio | stdio or http |
--host / --port | — | 127.0.0.1 / 8000 | HTTP bind address |
--auth-token | EMBEDDEDCI_MCP_TOKEN | — | require Authorization: Bearer (mandatory off loopback) |
--allowed-host | — | — | Host header(s) to accept on a network bind (DNS-rebinding protection) |
--allow-unauthenticated | — | off | serve a network address without a token (isolated networks only) |
Run the server on the machine next to the pod, and point clients at it:
export EMBEDDEDCI_MCP_TOKEN=$(openssl rand -hex 32)
embeddedci-mcp --transport http --host 0.0.0.0 --connection 192.168.1.213 --la-voltage 3.3
claude mcp add --transport http benchpod http://bench-host:8000/mcp \
--header "Authorization: Bearer $EMBEDDEDCI_MCP_TOKEN"
The server drives real hardware, so it refuses a non-loopback bind without a token. It holds one pod connection shared by all HTTP clients, and serialises their tool calls.
Every tool, grouped as in the server. Parameters in bold are required; the others are optional and show their default when they have one (no default means "from the wiring profile", "keep the current setting" or "not used"). Units are volts, amps, seconds and hertz. LA channel arguments take a number (1-14) or a name from the wiring profile. Each tool's input schema carries the full description, ranges and enums, so an agent sees more than this table.
| Tool | Purpose | Parameters |
|---|---|---|
connect | Open a connection (closing any previous one) and report status, capabilities and where the wiring profile came from. Without a connection or a configured default (--connection, BENCHPOD_CONNECTION, the CLI's saved connection), finds the one pod on the LAN over mDNS. | connection, la_voltage, lease_wait=30 |
disconnect | Close UART/CAN sessions and the connection, releasing a cloud lease. | none |
status | Firmware, capabilities, LA voltage, open sessions and warnings (works when not connected). | none |
set_la_voltage | Select the LA I/O voltage to match the DUT (1.8 V needs a rev3 pod). | `voltage` |
| Tool | Purpose | Parameters |
|---|---|---|
cloud_list_devices | The pods on your embeddedci.com organization and whether each is online, without connecting. | none |
| Tool | Purpose | Parameters |
|---|---|---|
wiring | Which DUT signal is on which LA channel, plus the power rail, UART baud and SWD target. | none |
set_wiring | Replace the wiring profile for this connection, or store it on embeddedci.com. | `profile`, save=false |
| Tool | Purpose | Parameters |
|---|---|---|
power_on | Switch the target's power rail on (optionally scheduled pod-side). | efuse, delay |
power_off | Switch the target's power rail off. | efuse, delay |
power_status | Both target-power rails, internal 5 V (efuse 1) and external (efuse 2): on/off, tripped, bus voltage and current, and the pod's own draw. | none |
reset_target | Drive the DUT's reset line from the pod's reset pin. | action=pulse, pulse=0.1 |
| Tool | Purpose | Parameters |
|---|---|---|
measure_power | Sample supply current and voltage for a window: average, min, peak, energy and charge. | `duration`, efuse, rate_hz=500, points=0 |
power_profile_start | Start sampling the rail in the background while other tools run. | efuse, rate_hz=500, max_duration=60 |
power_profile_stop | Stop the running profile and return its statistics (and a trace). | points=0 |
| Tool | Purpose | Parameters |
|---|---|---|
flash | Program the DUT over SWD through the pod's CMSIS-DAP probe: a local file (OpenOCD runs next to the server), or a build uploaded to embeddedci.com (build id or latest, repo, ref; embeddedci.com runs OpenOCD on a cloud connection, LAN/USB downloads it). | swclk, swdio, target, file, nreset, load_address, target_power, verify=true, reset=true, connect_under_reset, extra_configs, extra_args, timeout=300, connect_attempts=5, build, repo, ref, artifact, server_side |
| Tool | Purpose | Parameters |
|---|---|---|
spi_flash_info | Read the JEDEC ID and size of the SPI NOR flash on the SPI pins. | sck, mosi, miso, cs, hz=1000000, mode=0 |
spi_flash_program | Erase, write and verify an image in the SPI NOR flash. | `file`, addr=0, erase=true, verify=true, hold_reset=false, sck, mosi, miso, cs, hz=6000000, mode=0 |
spi_flash_read | Read flash bytes to a file, or up to 4096 bytes as hex. | `addr`, `length`, file, sck, mosi, miso, cs, hz=6000000, mode=0 |
spi_transfer | One full-duplex SPI transaction with any device on the SPI pins. | `tx_hex`, sck, mosi, miso, cs, hz=1000000, mode=0 |
| Tool | Purpose | Parameters |
|---|---|---|
capture_uart | Record the DUT's UART for a window, or until a regex matches. | `duration`, rx, tx, baud, until_regex |
| power_cycle_and_capture | Power-cycle the target and capture UART across the boot. | rx, tx, efuse, delay=1, duration=4, baud, until_regex,
只显示了开头部分;其余内容请在仓库中阅读