npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@neural-tools/cli

v0.1.6

Published

CLI for Neural Tools - Generate MCPs, Claude commands, and AI workflows

Readme

@neural-tools/cli

CLI for Neural Tools - Generate MCPs, Claude commands, and AI workflows

npm version License: MIT

The main CLI tool for Neural Tools, providing commands to generate MCP servers, Claude commands, agents, and deploy AI-powered applications.

Installation

Global Installation (Recommended)

npm install -g @neural-tools/cli

Project-specific

npm install --save-dev @neural-tools/cli

Using npx (No installation)

npx @neural-tools/cli <command>

Usage

neural-tools <command> [options]

Available Commands

generate mcp

Generate a FastMCP server with Python templates.

neural-tools generate mcp <name> [options]

Options:
  -d, --description <desc>      Description of the MCP server
  -o, --output <dir>            Output directory (default: ./apps)
  --cicd <provider>             CI/CD provider (github, harness, none)
  --deployment <platform>       Deployment platform (aws, gcp, none)
  --dry-run                     Preview without creating files

Example:

neural-tools generate mcp github-integration \
  --description "GitHub API integration server" \
  --cicd github \
  --deployment aws

This creates:

  • Complete FastMCP server with Python
  • Docker configuration
  • CI/CD workflow files
  • Deployment templates (if specified)

generate command

Generate a Claude Code slash command.

neural-tools generate command <name> [options]

Options:
  -d, --description <desc>    Description of the command
  -o, --output <dir>          Output directory (default: ./claude/commands)
  --args <arguments...>       Command arguments
  --tools <tools...>          Allowed tools for Claude
  --global                    Install globally to ~/.claude/commands
  --dry-run                   Preview without creating files

Example:

neural-tools generate command search-docs \
  --description "Search project documentation" \
  --args query \
  --tools "Read" "Grep" "Bash"

This creates a slash command that can be used in Claude Code as /search-docs <query>.


generate agent

Generate a specialized Claude agent.

neural-tools generate agent <name> [options]

Options:
  -d, --description <desc>    Description of the agent
  -o, --output <dir>          Output directory (default: ./claude/agents)
  --model <model>             Model to use (sonnet, opus, haiku)
  --tools <tools...>          Available tools
  --global                    Install globally to ~/.claude/agents
  --dry-run                   Preview without creating files

Example:

neural-tools generate agent code-reviewer \
  --description "Automated code review agent" \
  --model opus \
  --tools "Read" "Grep" "Edit"

deploy

Deploy an MCP server to AWS or GCP.

neural-tools deploy <name> [options]

Options:
  -p, --platform <platform>    Deployment platform (aws, gcp)
  --region <region>            Cloud region
  --env <env>                  Environment (dev, staging, prod)

Example:

neural-tools deploy github-integration \
  --platform aws \
  --region us-east-1 \
  --env production

login

Manage your Neural Tools license (optional).

neural-tools login [options]

Options:
  --key <key>    License key

Note: All features are free and available without a license.


status

View current status and available features.

neural-tools status

Shows:

  • License information (if configured)
  • Available features (all features are enabled)
  • Quick start commands

Project Structure

When you use the CLI, it creates organized project structures:

my-project/
├── apps/                    # Generated MCP servers
│   └── mcp-github/
│       ├── server.py
│       ├── Dockerfile
│       └── requirements.txt
├── claude/
│   ├── commands/           # Slash commands
│   │   └── search-docs.md
│   └── agents/             # Specialized agents
│       └── code-reviewer.md
└── package.json

Configuration

The CLI reads configuration from:

  • package.json (workspace settings)
  • .env (environment variables)
  • ~/.ai-toolkit/ (user settings)

Development

# Clone the repository
git clone https://github.com/MacLeanLuke/neural-tools.git
cd neural-tools/packages/cli

# Install dependencies
pnpm install

# Build
pnpm build

# Run locally
node dist/cli.js --help

Examples

Create a GitHub MCP Server

neural-tools generate mcp github \
  --description "GitHub API integration" \
  --cicd github \
  --deployment aws

Create a Knowledge Base Search Command

neural-tools generate command search-kb \
  --description "Search vector database" \
  --args query \
  --tools "Read" "Bash"

Deploy to AWS

neural-tools deploy github \
  --platform aws \
  --region us-east-1 \
  --env prod

Dependencies

  • @neural-tools/core - Core utilities and types
  • commander - CLI framework
  • inquirer - Interactive prompts
  • execa - Process execution
  • fs-extra - Enhanced file system operations

Contributing

Contributions are welcome! See the main repository for guidelines.

License

MIT - See LICENSE.md for details.

Links