Skip to main content

A powerful CLI for interacting with the ASI:One LLM and Model Context Protocol (MCP) servers

Project description

ASI1 MCP CLI

A powerful command-line interface for interacting with the ASI:One LLM and Model Context Protocol (MCP) servers. This CLI provides seamless access to AI capabilities combined with real-time web search, file operations, and more.

Features

  • 🤖 ASI:One AI Integration - Powered by ASI:One's advanced language model
  • 🔍 Brave Search - Real-time web search capabilities
  • 📁 File Operations - Read, write, and manage files
  • 🎥 YouTube Integration - Video summarization and analysis
  • 💾 Conversation Memory - Persistent chat history
  • 🛠️ MCP Server Support - Extensible with additional MCP servers

Quick Start

Installation

pip install asi1-mcp-cli

Setup

  1. Create configuration directory:

    mkdir -p ~/.asi1
    
  2. Create configuration file:

    # Copy the example config
    cp $(python -c "import asi1_mcp_cli; import os; print(os.path.join(os.path.dirname(asi1_mcp_cli.__file__), '..', 'asi1-mcp-server-config-example.json'))") ~/.asi1/config.json
    
  3. Edit the configuration:

    nano ~/.asi1/config.json
    

    Update the following fields:

    • api_key: Your ASI:One API key
    • BRAVE_API_KEY: Your Brave Search API key (optional)

Usage

Basic Conversation

asi1 "What is the capital of France?"

Web Search

asi1 "What are the latest developments in quantum computing?"

List Available Prompts

asi1 --list-prompts

Use Specific Prompt Templates

# Code review
asi1 --prompt review

# Git commit
asi1 --prompt commit

# YouTube video summary
asi1 --prompt yt --url "https://www.youtube.com/watch?v=example"

Configuration

The configuration file (~/.asi1/config.json) supports:

LLM Settings

  • provider: LLM provider (use "asi-one" for ASI:One)
  • model: Model name (e.g., "asi1-mini")
  • api_key: Your API key
  • temperature: Response creativity (0.0-1.0)
  • base_url: API endpoint

MCP Servers

  • Brave Search: Web search capabilities
  • YouTube: Video analysis and summarization
  • File Operations: Read/write files
  • Commands: Execute system commands (with confirmation)

Prompt Templates

Built-in Templates

  1. review - Code review assistant

    • Analyzes git changes and provides feedback
  2. commit - Git commit assistant

    • Creates conventional commit messages
  3. yt - YouTube video summarizer

    • Summarizes video content with bullet points

Custom Templates

Add your own prompt templates to the configuration:

{
  "prompts": {
    "my_template": {
      "template": "You are a helpful assistant. {user_input}",
      "arguments": []
    }
  }
}

Examples

Software Development

# Code review
asi1 --prompt review

# Create commit message
asi1 --prompt commit

# Ask about programming
asi1 "How do I implement a REST API in Python?"

Research & Information

# Current events
asi1 "What are the latest developments in AI?"

# Technical research
asi1 "What are the differences between React and Vue.js?"

# Market analysis
asi1 "What's the current state of the cryptocurrency market?"

Content Creation

# Video summarization
asi1 --prompt yt --url "https://www.youtube.com/watch?v=example"

# Writing assistance
asi1 "Help me write a professional email to a client"

Troubleshooting

Common Issues

  1. "No module named 'langchain_openai'"

    pip install langchain-openai
    
  2. "404 page not found"

    • Check your base_url in config (should be https://api.asi1.ai/v1)
  3. MCP server errors

    • Some servers require additional setup (e.g., API keys)
    • Check the server configuration in your config file

Getting Help

  • Check the configuration file syntax
  • Ensure all required dependencies are installed
  • Verify API keys are correct
  • Check network connectivity

Development

Local Development Setup

git clone <repository-url>
cd asi1-mcp-cli
pip install -e .

Running Tests

pytest

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Support

For support, please open an issue on the GitHub repository or contact the maintainers.

Project details


Download files

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

Source Distribution

asi1_mcp_cli-0.1.2.tar.gz (19.3 kB view details)

Uploaded Source

Built Distribution

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

asi1_mcp_cli-0.1.2-py3-none-any.whl (21.6 kB view details)

Uploaded Python 3

File details

Details for the file asi1_mcp_cli-0.1.2.tar.gz.

File metadata

  • Download URL: asi1_mcp_cli-0.1.2.tar.gz
  • Upload date:
  • Size: 19.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.7

File hashes

Hashes for asi1_mcp_cli-0.1.2.tar.gz
Algorithm Hash digest
SHA256 df1d5403c7337fd2cb8196037d62f4c7844b11bc95ad7dd87ffb8a9f5bc635a2
MD5 9a3b4d161969a8d28206976baf383f14
BLAKE2b-256 1278d10dffa8bc5742502e8785a14e34b27dee387b66d59279dcdb02648b5115

See more details on using hashes here.

File details

Details for the file asi1_mcp_cli-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: asi1_mcp_cli-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 21.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.7

File hashes

Hashes for asi1_mcp_cli-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 5da978f23cba356f8f351785c0ced5b784690ecc8a31b3896e9e18656881255b
MD5 140314b8da42dd6f267c991586848e4e
BLAKE2b-256 9d0a47598a25af9d33212c083bd06633a5d4e1f40511f9176499e4e438a6fbaa

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