What is heatpump-mcp-server CLAUDE.md?

Repository instructions for a Model Context Protocol server that helps AI clients calculate residential heat-pump sizing, costs, and cold-weather performance. They document the project structure, setup commands, server startup, code checks, and tests.

Use them when developing the heat-pump server, installing its Python package, running it for MCP clients, formatting or linting code, and running tests.

They give coding agents the project-specific information needed to install, run, check, and test the server consistently.

How jiweiqi/heatpump-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jiweiqi/heatpump-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/jiweiqi/heatpump-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jiweiqi/heatpump-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/jiweiqi/heatpump-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/jiweiqi/heatpump-mcp-server/claude-md)

Your own site

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

Per session 1,547 This file is loaded in full into every session.

When invoked 1,547 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	$0.01547	$0.01547
Opus 5	$0.00773	$0.00773
Sonnet 5	$0.00309	$0.00309
Haiku 4.5	$0.00155	$0.00155

Measured 9d ago against content hash c3d7c9c4c86c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

heatpump-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 9d 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 · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 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.

Project Overview

HeatPump MCP Server is a Model Context Protocol (MCP) server for residential heat pump sizing, cost estimation, and cold-climate performance verification. It exposes heat pump calculation tools to AI assistants like Claude Desktop, Claude Code, Cursor, and other MCP clients.

Key Feature: Works out-of-the-box with bundled data - no API keys required.

Development Commands

Package Management

# Install package in editable mode with dev dependencies
uv pip install -e ".[dev]"

# Install from source
uv pip install -e .

Running the Server

# Run server directly
python -m heatpump_mcp_server.server

# Or use the installed entry point
heatpump-mcp-server

# Using uvx (recommended for end users)
uvx --from . heatpump-mcp-server

Code Quality

# Lint code
ruff check .

# Format code
ruff format .

Testing

# Run tests (if test suite exists)
pytest

# Run tests with coverage
pytest --cov=heatpump_mcp_server

Architecture

Built on FastMCP for easy MCP server development.

Core Components

server.py: Main MCP server that registers tools, resources, and prompts
tools.py: MCP tool definitions (the calculators exposed to AI assistants)
resources.py: MCP resources for data access (design temps, heat pump models, climate zones)
prompts.py: Guided prompts for common workflows
config.py: Configuration via pydantic-settings (loads from .env or environment)

Service Layer Architecture

The project follows a service-based architecture where business logic is separated into domain-specific services:

services/quick_sizer_service.py: Single-zone BTU sizing with climate-zone-specific coefficients
services/multi_zone_service.py: Floor-by-floor load calculations
services/bill_estimator_service.py: Energy cost comparison and payback analysis
services/cold_climate_service.py: Heat pump capacity verification at design temperature
services/electricity_rate_service.py: Electricity rate lookups (EIA API or bundled state averages)
services/heat_pump_models_service.py: Heat pump model database access
services/design_temp_service.py: Climate data and design temperature lookups
services/capacity_curve_service.py: Heat pump capacity derating calculations

Read the full file on GitHub · 193 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.

9d ago First seen · 193 lines · 1,547 tokens per session scan A c3d7c9c4c86c

Subscribe to this mod's changes

heatpump-mcp-server CLAUDE.md is an instructions file published in the GitHub repository jiweiqi/heatpump-mcp-server (3 stars, last pushed 10mo ago), licensed MIT. It adds 1,547 tokens to every session, about $0.0077 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 IoT

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

heatpump-mcp-server: Instructions file for Claude Code