What is thermal-mcp-server CLAUDE.md?

Repository instructions for AI coding agents working on thermal-mcp-server, a Python service that provides liquid-cooling analysis for GPUs. They explain its architecture, physics model, tools, and supported engineering assumptions.

Use them when modifying the server, its validation models, thermal calculations, MCP tool wrappers, or public analysis functions.

They tell an agent what the thermal model does and does not represent, helping prevent changes that contradict the project's documented physics.

How riccardovietri/thermal-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to riccardovietri/thermal-mcp-server. 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/riccardovietri/thermal-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/riccardovietri/thermal-mcp-server

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/riccardovietri/thermal-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/riccardovietri/thermal-mcp-server/claude-md)

Your own site

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

Per session 1,888 This file is loaded in full into every session.

When invoked 1,888 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	$0.01888	$0.01888
Opus 5.5	$0.00755	$0.00755
Sonnet 5.5	$0.00378	$0.00378
Haiku 4.5	$0.00189	$0.00189

Measured 1mo ago against content hash 00a1cae2c801, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

thermal-mcp-server 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 1mo 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 · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — thermal-mcp-server

Project context for all coding agents (Claude Code, Codex, etc.). Read before making changes. For durable project decisions, read docs/decisions.md.

What this is

A Python thermal-hydraulic screening engine for liquid-cooled GPU cold plates, with a thin MCP interface. Target audience: data center thermal engineers, AI infrastructure teams. Goal: auditable thermal design decisions supported by explicit model assumptions and evidence. MCP is an interface, not the product.

Architecture in 30 seconds

schemas.py          ← Pydantic I/O models, validation, defaults
physics.py          ← All math: 1D resistance network, Dittus-Boelter, Darcy-Weisbach
decision_report.py  ← Scoped thermal screening, input provenance, stress scenarios
mcp_server.py       ← FastMCP tool wrappers (thin — no physics here)

Five MCP tools: analyze_coldplate, compare_coolants, optimize_flow_rate, analyze_rack, generate_decision_report. Public Python API: analyze(), analyze_rack(), and optimize_flow() in physics.py.

Physics: what the model does and does not do

Does:

Steady-state 1D resistance network: R_jc → R_tim → R_base → R_conv
Rectangular channel hydraulic diameter: Dh = 2wh/(w+h)
Dittus-Boelter Nu for turbulent, Nu=4.36 for laminar, linear blend 2300–4000
Darcy-Weisbach ΔP with Blasius friction, same transition blend
Pump power = ΔP × Q / 0.50 (50% efficiency assumption, documented inline)
Binary-search flow optimization
Rack-level model: N identical GPUs in series or parallel topology (see docs/physics.md Section G)

Does not (known limitations, do not paper over):

No manifold/header pressure losses (rack model uses cold plate ΔP only)
No heterogeneous GPU racks (all GPUs assumed identical)
No transient thermal capacitance
No 2D spreading resistance
No temperature-dependent fluid properties
No flow maldistribution across channels or parallel branches
No boiling/two-phase

These are documented in docs/physics.md sections E and G. Do not add hacks to simulate them — add them properly or leave them out.

Read the full file on GitHub · 179 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.

1mo ago Changed · +4 lines · +62 tokens per session 00a1cae2c801
2mo ago First seen · 175 lines · 1,826 tokens per session scan A 6818f29632e7

Subscribe to this mod's changes

thermal-mcp-server CLAUDE.md is an instructions file published in the GitHub repository riccardovietri/thermal-mcp-server (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,888 tokens to every session, about $0.0076 per session on Opus 5.5. 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.

Backend and APIs Scientific datacenter gpu-cooling liquid-cooling mcp thermal-engineering

thermal-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
thermal-mcp-server CLAUDE.mdriccardovietri/thermal-mcp-server	Instructions file	1	1mo ago	MIT	A	1,888	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

thermal-mcp-server: Instructions file for Claude Code