EmbeddedCI BenchPod

embeddedci-mcp

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.

Requirements

• Python 3.10+ and uv (for uvx), or pip.
• A BenchPod reachable over the network, the embeddedci.com cloud, or USB. With firmware 3.9.0 and later, connection 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).
• For 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.

Set up your client

Claude Code

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:

1. its connection argument;
2. the server default, --connection;
3. BENCHPOD_CONNECTION;
4. the default connection benchpod-cli saved with benchpod set-connection (read-only, from ~/.config/benchpod-cli/config.json, or under $XDG_CONFIG_HOME);
5. mDNS discovery of the one pod on the LAN.

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 / Cursor

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" } } } }

Codex

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" }

A pod in the cloud

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.

Options

Serving a bench over HTTP

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.

Tools

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.

Connection

Cloud (embeddedci.com)

Wiring profile

Power

Power profiles

Flash

SPI flash and SPI devices

UART

| power_cycle_and_capture | Power-cycle the target and capture UART across the boot. | rx, tx, efuse, delay=1, duration=4, baud, until_regex,