@neural-tools/cli
v0.1.6
Published
CLI for Neural Tools - Generate MCPs, Claude commands, and AI workflows
Maintainers
Readme
@neural-tools/cli
CLI for Neural Tools - Generate MCPs, Claude commands, and AI workflows
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/cliProject-specific
npm install --save-dev @neural-tools/cliUsing 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 filesExample:
neural-tools generate mcp github-integration \
--description "GitHub API integration server" \
--cicd github \
--deployment awsThis 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 filesExample:
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 filesExample:
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 productionlogin
Manage your Neural Tools license (optional).
neural-tools login [options]
Options:
--key <key> License keyNote: All features are free and available without a license.
status
View current status and available features.
neural-tools statusShows:
- 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.jsonConfiguration
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 --helpExamples
Create a GitHub MCP Server
neural-tools generate mcp github \
--description "GitHub API integration" \
--cicd github \
--deployment awsCreate 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 prodDependencies
- @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.
