ppk2-mcp
MCP server for Nordic Semiconductor's Power Profiler Kit II (PPK2), enabling current measurement and device control via 12 tools from Claude.
README
ppk2-mcp
MCP server for Nordic Semiconductor's Power Profiler Kit II (PPK2). Provides 12 tools for discovering, connecting, configuring, and measuring current draw directly from Claude Code or Claude Desktop.
Features
- Discover PPK2 devices on USB
- Connect with automatic calibration loading
- Configure source/ampere mode and supply voltage
- Measure current at ~100 kHz native sample rate
- Log raw measurements to timestamped CSV files
- Inspect saved logs without leaving the conversation
Requirements
- Python 3.10+
- Nordic Semiconductor PPK2 hardware
- USB connection to PPK2
Quick Start
git clone https://github.com/Ultrahuman-tech/ppk2-mcp.git
cd ppk2-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Then configure your MCP client (see below).
Configuration
Claude Code
Add to ~/.claude.json under mcpServers:
{
"mcpServers": {
"ppk2": {
"command": "/path/to/ppk2-mcp/.venv/bin/python3",
"args": ["/path/to/ppk2-mcp/ppk2_server.py"],
"type": "stdio"
}
}
}
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"ppk2": {
"command": "/path/to/ppk2-mcp/.venv/bin/python3",
"args": ["/path/to/ppk2-mcp/ppk2_server.py"]
}
}
}
Replace /path/to/ppk2-mcp with the actual clone location.
Tools Reference
| Tool | Description |
|---|---|
list_devices |
Scan USB for connected PPK2 devices |
connect |
Connect to a PPK2 and load calibration (returns session ID) |
disconnect |
Disconnect, stop measurement, power off DUT |
set_mode |
Set operating mode: source (PPK2 powers DUT) or ampere (external power) |
set_voltage |
Set supply voltage in mV (source mode only, 800-5000 mV) |
power_control |
Toggle DUT power on/off |
get_session_info |
Show current session state |
start_measuring |
Begin continuous current measurement |
stop_measuring |
Stop continuous measurement |
measure |
Atomic: start, collect for N seconds, stop, save CSV, return stats |
list_logs |
List saved measurement CSV files |
get_log |
Read a saved log file (metadata + first N rows) |
Typical Workflow
list_devices → find PPK2 on USB
connect → get session_id
set_mode "source" → PPK2 supplies power
set_voltage 3300 → 3.3V to DUT
power_control "on" → power up the device
measure 5.0 → capture 5 seconds of current data
disconnect → clean up
Logs
Raw measurement data is saved to the logs/ directory as timestamped CSV files. Each file contains:
- Comment header with metadata (date, duration, mode, voltage, sample count, sample rate)
- CSV data columns:
sample_idx,current_ua(optionallydigitalfor digital channels)
Example:
# PPK2 Raw Measurement Log
# Date: 2025-02-18 19:57:00
# Duration: 2.01s
# Mode: source
# Voltage: 3300 mV
# Samples: 200,544
# Sample Rate: 99,773 sps
sample_idx,current_ua
0,1523.45
1,1518.22
...
Known Issues
- Stale serial buffer on reconnect: After a previous session crashes or is interrupted, the PPK2's serial buffer may contain leftover binary measurement data. The server handles this automatically by flushing the buffer before reading calibration data.
- Metadata decode errors: The upstream
ppk2-apilibrary can crash on binary noise in the serial buffer. This server includes a built-in patch (latin-1 fallback) so no manual library edits are needed.
License
MIT - see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.