Overview: MCP CLI - Model Context Provider Command Line Interface

📌 Title

MCP CLI - Model Context Provider Command Line Interface
A powerful, feature-rich command-line tool for interacting with Model Context Provider (MCP) servers, enabling seamless communication with Large Language Models (LLMs) via the CHUK-MCP protocol.

🛠️ How to Use

Installation

From Source:

git clone https://github.com/chrishayuk/mcp-cli  
cd mcp-cli  
pip install -e ".[cli,dev]"

Using UV (Alternative):

uv sync --reinstall  
uv run mcp-cli --help

Running the CLI

Chat Mode:
```
mcp-cli chat --server sqlite  
```
Interactive Mode:
```
mcp-cli interactive --server sqlite  
```

Command Mode (for automation):

mcp-cli cmd --server sqlite --input file.txt --prompt "Summarize: {{input}}"

🌟 Key Features

Multiple Modes:
- Chat Mode – Conversational LLM interaction with automated tool usage.
- Interactive Mode – Command-driven server operations.
- Command Mode – Scriptable automation for pipelines.
- Direct Commands – Run single commands without entering interactive mode.
Multi-Provider Support:
- OpenAI (gpt-4o, gpt-4-turbo)
- Ollama (llama3.2, qwen2.5-coder)
- Extensible for additional providers.
Advanced Tool System:
- Automatic tool discovery & execution.
- Tool call history tracking.
- Multi-step tool chain support.
Conversation Management:
- Full history tracking.
- JSON export & compaction.
- Filtering by message ranges.
Rich UX:
- Command autocompletion.
- Colorful output & progress indicators.
- Detailed help docs.
Resilient Resource Handling:
- Graceful error recovery.
- Clean terminal restoration.
- Multi-server connection support.