What is plr-mcp CLAUDE.md?

Instructions for using plr-mcp, an MCP server that exposes laboratory instruments such as liquid handlers, plate readers, thermocyclers, and heater-shakers as tools. It covers simulation and connections to real equipment.

Use them when connecting Claude Code to plr-mcp, testing protocols in simulation, or preparing work on laboratory hardware.

They explain safety checks for simulated work and for operations that can move physical equipment or liquids.

How di-omics/plr-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to di-omics/plr-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/di-omics/plr-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/di-omics/plr-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/di-omics/plr-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/di-omics/plr-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/di-omics/plr-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/di-omics/plr-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/di-omics/plr-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/di-omics/plr-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,472 This file is loaded in full into every session.

When invoked 1,472 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01472	$0.01472
Opus 5	$0.00736	$0.00736
Sonnet 5	$0.00294	$0.00294
Haiku 4.5	$0.00147	$0.00147

Measured 8d ago against content hash a3efc7db143c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

plr-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 8d 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 · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

plr-mcp — guide for Claude Code

An MCP server that exposes PyLabRobot (liquid handler, plate reader, thermocycler, heater-shaker) as tools. It ships in simulation by default and can drive real instruments. Some tools move a physical arm and liquid, so read the safety rules before doing anything on a non-chatterbox backend.

Safety rules (read first)

Simulation is the default and the safe place to work. The chatterbox backend performs no motion. Do everything you can there first.
simulated: true is NOT a measurement. Every tool result carries a simulated flag. If it is true, the numbers came from a stub with no instrument attached — never report them as real data.
Never call a destructive tool on real hardware until it is homed. On star/ot2/evo, liquid-handling tools stay blocked until plr_setup_deck(home=true) runs on a physically clear deck. Homing moves the arm; a human must confirm the deck is clear first.
Real protocol runs are human-gated. plr_run_pcr_enrichment_round1 on star refuses to run without confirm=true. Do not set confirm=true yourself — ask the operator to, with a person watching the deck.
One driver on the USB at a time. The server tears down a link before opening another. Don't spawn a second process against the same instrument.
Tool annotations encode this: readOnlyHint tools are safe probes; destructiveHint tools can move hardware. Respect them.

How Claude Code connects

This repo ships .mcp.json, so opening it in Claude Code prompts you to enable the plr server (approve once; check /mcp or claude mcp list). Tools then appear prefixed plr_ (e.g. plr_aspirate). .mcp.json pins PLR_MCP_BACKEND=chatterbox, so the server starts in simulation. Requires pip install -e . so the plr-mcp console script is on PATH.

Tools

Probes — read-only, safe to repeat:

plr_connect_check — zero-motion pre-flight against a real instrument.
plr_deck_state — what's on the deck.
plr_read_plate — absorbance / fluorescence / luminescence.

Read the full file on GitHub · 113 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.

8d ago First seen · 113 lines · 1,472 tokens per session scan A a3efc7db143c

Subscribe to this mod's changes

plr-mcp CLAUDE.md is an instructions file published in the GitHub repository di-omics/plr-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,472 tokens to every session, about $0.0074 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 2026-09-01.

Hardware and IoT Scientific ai-agents audit-trail automation lab-automation liquid-handling mcp

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

plr-mcp: Instructions file for Claude Code