mcpField
G
GNNEPCSAFT MCP Server

GNNEPCSAFT MCP Server

Local
github.com/wildsonbblScience & Education0Updated 1w ago
Repository

About GNNEPCSAFT MCP Server

GNNEPCSAFT MCP Server exposes GNNEPCSAFT tools through MCP. It uses graph neural networks to estimate PC-SAFT pure-component parameters and FeOs for calculations, supporting property prediction for molecules and mixtures.

Key features

  1. 01Estimate PC-SAFT pure-component parameters
  2. 02Predict density and vapor pressure
  3. 03Use FeOs for PC-SAFT calculations

Use cases

  1. 01Predicting density or vapor pressure of molecules
  2. 02Predicting properties of mixtures

MCP support

The MCP server exposes GNNEPCSAFT tools to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "gnnepcsaft_mcp_server": {
      "command": "uvx",
      "args": [
        "gnnepcsaft-mcp-server"
      ]
    }
  }
}
Run commanduvx gnnepcsaft-mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypignnepcsaft-mcp-server

Tools

12

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
smilesarrayYes

Details

From the project README

GNNPCSAFT MCP Server

GNNPCSAFT MCP Server is an implementation of the Model Context Protocol (MCP) for GNNPCSAFT tools. GNNPCSAFT leverages Graph Neural Networks (GNNs) to estimate PC-SAFT pure-component parameters, allowing property predictions such as density and vapor pressure for any molecule or mixture. FeOs is used for PC-SAFT calculations.

Other implementations with GNNPCSAFT:

How to Use

Installation

You need uvx installed.

Starting the Server
uvx --from gnnepcsaft-mcp-server gnnpcsaftmcp
Example: Claude Desktop Configuration
{
  "mcpServers": {
    "gnnpcsaft": {
      "command": "uvx",
      "args": ["--from", "gnnepcsaft-mcp-server", "gnnpcsaftmcp"]
    }
  }
}

License

GNU General Public License v3.0

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.