agentmods.dev

multicomp-mcp CLAUDE.md

multicomp-mcp CLAUDE.md is an instructions file for coding agents from cameroncoats/multicomp-mcp. It costs 938 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that lets AI agents control a Multicomp Pro bench power supply and its built-in multimeter over USB serial.

In plain words
What is it for?
Running the server, discovering or selecting the power supply, checking its status, controlling power, and testing tool functions against the connected device.
Why use it?
They explain the project's commands, hardware connection, architecture, and testing method so an agent can work with the real instrument safely and consistently.

Instructions file

not rated 0 1mo ago A scan 938 tokens original MIT
View the source file cameroncoats/multicomp-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/cameroncoats/multicomp-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/cameroncoats/multicomp-mcp

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for multicomp-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cameroncoats/multicomp-mcp/claude-md.svg)](https://agentmods.dev/instructions/cameroncoats/multicomp-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cameroncoats/multicomp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cameroncoats/multicomp-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 938 This file is loaded in full into every session.
When invoked 938 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00938 $0.00938
Opus 5 $0.00469 $0.00469
Sonnet 5 $0.00188 $0.00188
Haiku 4.5 $0.00094 $0.00094

Measured 4d ago against content hash 94f5f7ee02b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

multicomp-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

An MCP server (Python, FastMCP + pyserial) that lets LLM agents control a Multicomp Pro MP711134 bench power supply with built-in multimeter — a rebadged OWON SPM-series unit speaking SCPI over USB serial. The tools are designed around agent flows (blocking wait_for, power_cycle, host-driven run_profile waveforms) rather than 1:1 SCPI mapping.

Commands

Uses uv for everything; there is no test suite, linter, or CI.

  • Run the server: uv run multicomp-mcp (stdio MCP server; registered for this project via .mcp.json)
  • Ad-hoc testing is done live against the real instrument by importing the tool functions directly: uv run python -c "import sys; sys.path.insert(0, 'src'); from multicomp_mcp import server; print(server.get_status())"
  • Environment: MULTICOMP_PORT overrides discovery; MULTICOMP_BAUD (default 115200). Auto-discovery enumerates USB serial ports, tries CH340 (1a86:7523) adapters first, and confirms with *IDN? — the bridge chip has no unique USB identity, so the IDN probe is the fingerprint.

Architecture

Two modules under src/multicomp_mcp/:

  • scpi.py — transport + parsing. MP711134 owns the serial port (lazy open, exclusive, reconnect-on-error) and an RLock; all instrument I/O goes through query() (retries empty reads), command() (silent-success writes with a short ERR watch window), or write_unchecked() (fast path for paced streaming loops only). Verified setters (set_voltage etc.) write then confirm by readback. Parsed composite queries: measure_info() (MEAS:ALL:INFO? → V/I/P + trip flags + STANDBY/CV/CC/FAULT mode) and dmm_status() (CONF:ALL? → function/value/range, OL → value None).
  • server.py — FastMCP tool layer. Tools are sync functions holding psu.lock for their whole duration (long-running tools like wait_for/capture/run_profile poll inside the lock). Docstrings ARE the tool descriptions shown to agents — keep them accurate about behavior and hardware limits. Timeouts/durations are reported in results, not raised; hard caps: 300 s waits/profiles, 120 s captures.

Read the full file on GitHub · 40 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 40 lines · 938 tokens per session scan A 94f5f7ee02b4

Subscribe to this mod's changes

multicomp-mcp CLAUDE.md is an instructions file published in the GitHub repository cameroncoats/multicomp-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 938 tokens to every session, about $0.0047 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Hardware and IoTmcpowonpower-supplyscpitest-equipment
Related

Other instructions, from other repositories

cml-mcp AGENTS.md

AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).

xorrkaz/cml-mcp · 4,881 tokens

brilliant_sdk AGENTS.md

Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.

brilliantlabsAR/brilliant_sdk · 1,817 tokens

NeoMind CLAUDE.md

Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).

camthink-ai/NeoMind · 4,457 tokens

cad-cae-copilot copilot-instructions.md

Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.

armpro24-blip/cad-cae-copilot · 323 tokens

phone-mcp CLAUDE.md

Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.

premex-ab/phone-mcp · 2,128 tokens

zmk-config AGENTS.md

AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.

urob/zmk-config · 1,867 tokens