Neural Mcp

Overview

Neural Mcp is a GPU-accelerated MCP server designed for neural network training, deep learning, and model experimentation. By implementing the Model Context Protocol, it enables AI assistants to access neural network capabilities as callable tools, eliminating the need to switch between applications.

The server runs locally on your machine using the scicomp-neural-mcp Python package, installed via uvx. No authentication is required—it operates out of the box by communicating with MCP clients over stdio. Neural Mcp is released under the MIT license at version v0.1.6, with source code available at andylbrummer/math-mcp on GitHub.

Nested in the AI & Agents category on mcp.site, Neural Mcp works with any MCP client including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this project, claim your listing to earn the Verified badge and keep your information current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "neural_mcp": {
      "command": "uvx",
      "args": [
        "scicomp-neural-mcp"
      ]
    }
  }
}