What is the difference between this server and using sigrok‑cli directly?
The server wraps sigrok‑cli in an MCP interface, allowing LLMs to programmatically capture, decode, and analyze signals without manual command‑line use.
@KenosInc
Basic information
AI-powered logic analyzer control via Model Context Protocol - connect Claude, Cursor to sigrok-cli for automated signal capture and protocol decoding
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"sigrok": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--privileged",
"ghcr.io/kenosinc/sigrok-mcp-server"
]
}
}
}List all supported hardware drivers
List all supported protocol decoders
List all supported input file formats
List all supported output file formats
Show detailed info about a protocol decoder (options, channels, documentation)
Show detailed info about a hardware driver (functions, scan options, devices)
Show sigrok-cli and library version information
Scan for connected hardware devices
Capture communication data from a device and save to file
Decode protocol data from a captured file using protocol decoders
Check firmware file availability in sigrok firmware directories
This is an MCP server that integrates sigrok’s signal capture and protocol decoding with AI agents like Claude Code, Codex, and Cursor. It interfaces with logic analyzers and measurement devices via sigrok-cli, supporting over 100 protocols including I2C, SPI, UART, and CAN.
Run with Docker (docker pull ghcr.io/kenosinc/sigrok-mcp-server) or build from source with Go 1.25+ and sigrok-cli installed. Configure via environment variables (SIGROK_CLI_PATH, SIGROK_TIMEOUT_SECONDS, SIGROK_WORKING_DIR). On a client like Claude Desktop, add a JSON config pointing to the server command. Use tools such as scan_devices, capture_data, and decode_protocol for signal analysis.
The server wraps sigrok‑cli in an MCP interface, allowing LLMs to programmatically capture, decode, and analyze signals without manual command‑line use.
Some hardware drivers require firmware that cannot be bundled due to licensing. The server works without firmware for devices that don’t need it (e.g., `demo`, protocol‑only analysis). Use the `check_firmware_status` tool to verify availability.
It communicates over stdio (stdin/stdout JSON‑RPC).
Go 1.25+ and `sigrok‑cli` must be installed on the host, or you can run the Docker image. On Docker, access to USB devices may require `--privileged` and firmware volumes.
It supports all hardware that sigrok‑cli supports. Use `scan_devices` to discover connected devices; some may need firmware or driver configuration.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Testiny is a test case management platform. Its remote MCP server lets AI assistants such as Claude, ChatGPT, GitHub Copilot, Cursor and other MCP clients work directly with your Testiny data. Browse and search projects,

Design review for UI code, inside your agent. quick_review checks the files you just changed in about ten seconds. review_files returns a 0-100 score and patches. verify_fixes confirms the fixes landed, free. review_url
Comments