CoolpropMCP
MCP server exposing thermodynamic and transport properties of refrigerants and ~130 other fluids via CoolProp, enabling queries of state points, saturation, fluid info, and humid air properties through natural language.
README
CoolProp MCP Server
MCP server exposing thermodynamic and transport properties of refrigerants (and ~130 other fluids) from CoolProp.
All values are SI units: temperature K, pressure Pa (absolute), enthalpy/internal energy J/kg, entropy J/kg/K, density kg/m³, viscosity Pa·s, conductivity W/m/K.
Tools
| Tool | Purpose |
|---|---|
get_state |
Full state point (T, P, ρ, h, s, u, quality, cp, cv, μ, λ, speed of sound, Z, Pr, phase) from any two of T/P/D/H/S/U/Q |
get_property |
Single property at a state — any CoolProp output key |
get_saturation |
Saturated liquid + vapor states, latent heat and temperature glide at given T or P |
get_fluid_info |
Critical point, triple point, molar mass, T/P limits, GWP, ODP, normal boiling point |
get_humid_air_property |
Moist air properties for HVAC (enthalpy, humidity ratio, dew point, wet bulb, …) |
list_fluids |
Common refrigerants, or every CoolProp fluid |
list_property_keys |
Valid property keys and their units |
Fluid names follow CoolProp naming and aliases: R134a, R32, R410A,
R404A, R407C, R1234yf, R290 (propane), R600a (isobutane),
R744 (CO₂), R717 (ammonia), R718/Water, Air, …
Setup
python -m venv .venv
.\.venv\Scripts\python.exe -m pip install -r requirements.txt
Tests
.\.venv\Scripts\python.exe test_server.py # tool logic + reference values
.\.venv\Scripts\python.exe test_e2e.py # full MCP stdio round trip
Use with Claude Code
Registered user-scoped (available in every folder) with:
claude mcp add --scope user coolprop -- C:\Users\jerry.mansikkaviita\Desktop\CoolpropMCP\.venv\Scripts\python.exe C:\Users\jerry.mansikkaviita\Desktop\CoolpropMCP\server.py
Use with Claude Desktop
Add to %APPDATA%\Claude\claude_desktop_config.json:
{
"mcpServers": {
"coolprop": {
"command": "C:\\Users\\jerry.mansikkaviita\\Desktop\\CoolpropMCP\\.venv\\Scripts\\python.exe",
"args": ["C:\\Users\\jerry.mansikkaviita\\Desktop\\CoolpropMCP\\server.py"]
}
}
}
Example prompts
- "What is the enthalpy of saturated R134a vapor at −10 °C?" (remember: inputs in K/Pa)
- "Full state of R410A at 25 bar and 80 °C superheat"
- "Latent heat and glide of R407C at 5 bar"
- "GWP and critical point of R1234yf vs R134a"
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.
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.
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.
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.