Skip to main content

Secure MCP server with JAX-based numerical tools

Project description

HIDENNSIM - Secure MCP Server with JAX Integration

A licensed Model Context Protocol (MCP) server providing JAX-based numerical computation tools with hardware-bound license validation.

Features

  • ✅ MCP server with add_jax tool for floating-point addition using JAX
  • ✅ Layered security with Cython binary compilation
  • ✅ Hardware-bound license validation system
  • ✅ Cross-platform support (Windows, macOS, Linux)
  • ✅ Professional pip-installable distribution
  • ✅ Integration guides for Claude Desktop, Cursor, and ChatGPT

Quick Start

1. Create Virtual Environment (Recommended)

Creating a virtual environment isolates HIDENNSIM and its dependencies from your system Python, preventing conflicts with other projects.

macOS/Linux:

python3 -m venv hidennsim-env
source hidennsim-env/bin/activate

Windows (PowerShell):

python -m venv hidennsim-env
.\hidennsim-env\Scripts\Activate.ps1

Windows (Command Prompt):

python -m venv hidennsim-env
hidennsim-env\Scripts\activate.bat

Note: Your terminal prompt should now show (hidennsim-env) indicating the virtual environment is active.

2. Install HIDENNSIM

If you received a wheel file (.whl):

# Windows (PowerShell)
pip install C:\Path\To\hidennsim-1.0.0-cp313-cp313-win_amd64.whl

# macOS/Linux
pip install /path/to/hidennsim-1.0.0-cp313-cp313-win_amd64.whl

If published to PyPI (future):

pip install hidennsim

Note: If you received a wheel file directly, use the wheel installation method above. See CLIENT_INSTALLATION.md for detailed client installation instructions.

3. Install JAX

Choose the appropriate JAX installation for your system:

CPU-Only:

pip install "jax[cpu]"

GPU-Accelerated (NVIDIA GPU with CUDA):

pip install "jax[cuda12]"

4. Get Hardware Fingerprint

hidennsim-license hardware

5. Activate License

After purchasing your license, activate it:

hidennsim-license activate /path/to/license.key

6. Configure LLM

Claude Desktop Config Location

macOS:

~/Library/Application Support/Claude/claude_desktop_config.json

Windows:

%APPDATA%\Claude\claude_desktop_config.json

Linux:

~/.config/Claude/claude_desktop_config.json

Configuration

Add to your Claude Desktop config:

If virtual environment is active when starting Claude Desktop:

{
  "mcpServers": {
    "hidennsim": {
      "command": "hidennsim",
      "args": [],
      "env": {}
    }
  }
}

OR use full path to virtual environment executable:

macOS/Linux:

{
  "mcpServers": {
    "hidennsim": {
      "command": "/full/path/to/hidennsim-env/bin/hidennsim",
      "args": [],
      "env": {}
    }
  }
}

Windows:

{
  "mcpServers": {
    "hidennsim": {
      "command": "C:\\full\\path\\to\\hidennsim-env\\Scripts\\hidennsim.exe",
      "args": [],
      "env": {}
    }
  }
}

Documentation

System Requirements

  • Python: 3.10 or higher
  • Operating System: Windows 10+, macOS 12+, or Linux (Ubuntu 20.04+)
  • RAM: 4GB minimum (8GB recommended for GPU acceleration)
  • Disk Space: 1GB for installation

License

Proprietary - Contact support@hidennsim.com for licensing information.

Support

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

hidennsim-1.0.0-cp313-cp313-win_amd64.whl (123.9 kB view details)

Uploaded CPython 3.13Windows x86-64

File details

Details for the file hidennsim-1.0.0-cp313-cp313-win_amd64.whl.

File metadata

  • Download URL: hidennsim-1.0.0-cp313-cp313-win_amd64.whl
  • Upload date:
  • Size: 123.9 kB
  • Tags: CPython 3.13, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.9

File hashes

Hashes for hidennsim-1.0.0-cp313-cp313-win_amd64.whl
Algorithm Hash digest
SHA256 3ad0cb693b8833a34f960bc654107c53a17e4eeb03ee20f14fb0b89acefb73e1
MD5 b2268a5498b885816fee910fa9534ba7
BLAKE2b-256 a53dee34bacaf5c1523fde96cc92ed2d87895cbafc8fa70665ea1e13b2300c6f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page