Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
chrishayuk/mcp-cli
MCP CLI is a comprehensive command-line interface designed for seamless interaction with Model Context Protocol (MCP) servers. It supports multiple large language model (LLM) providers including OpenAI, Anthropic, Ollama, and custom providers, allowing users to switch dynamically between providers and models during conversations. The tool is built on a modular architecture integrating the CHUK Tool Processor for asynchronous tool execution and MCP server communication, and CHUK-LLM for unified LLM provider configuration and client management. The MCP CLI offers multiple operational modes tailored to different user needs: Chat Mode for conversational interaction with streaming responses and automated tool usage; Interactive Mode providing a command-driven shell for direct server operations; Command Mode designed for Unix-friendly automation and scripting; and Direct Commands for executing individual commands without entering interactive mode. This versatility makes it suitable for both interactive use and integration into automated workflows. Advanced features include real-time streaming responses with live UI updates, concurrent execution of multiple tools while maintaining conversation order, smart interruption capabilities, and detailed performance metrics such as response timing and execution statistics. The interface supports rich formatting including markdown rendering, syntax highlighting, and progress indicators, enhancing user experience. The tool system is robust, featuring automatic discovery and cataloging of server-provided tools, provider-specific adaptation of tool names, concurrent tool execution with progress displays, and a complete audit trail of tool usage. Configuration management is flexible, supporting environment variables, YAML and JSON config files, user preferences, and built-in validation and diagnostics. MCP CLI is cross-platform, supporting Windows, macOS, and Linux, with platform-specific optimizations. It offers colorful, formatted console output, context-aware command completion, comprehensive help documentation, and graceful error handling. Installation requires Python 3.11 or higher and appropriate API keys for LLM providers. Overall, MCP CLI is a powerful, feature-rich client for advanced interaction with MCP servers and LLMs, facilitating sophisticated conversation and tool management workflows.
https://github.com/chrishayuk/mcp-cli
Also in CLI Tools
yamadashy/repomix
Repomix is a tool that packs entire code repositories into single, AI-friendly files optimized for feeding Large Language Models and other AI tools, with features for token counting, security, and customization.
QwenLM/qwen-code
Open-source terminal coding agent in TypeScript from the Qwen team that consumes MCP servers as tool providers, alongside subagents, skills, hooks, IDE plugins and support for OpenAI, Anthropic, Gemini and Qwen APIs.
1jehuang/jcode
jcode is an extremely RAM-efficient and fast AI coding agent harness for the terminal, designed to optimize multi-session workflows.
txn2/kubefwd
kubefwd is a command-line tool that bulk port forwards Kubernetes services to a local machine, enabling seamless local development by accessing cluster services with their original names and connection strings.
davepoon/buildwithclaude
A comprehensive collection of specialized AI subagents, slash commands, and MCP server integrations designed to enhance the Claude Code AI development environment with powerful automation and domain-specific expertise.
av/harbor
Harbor is a containerized toolkit that enables effortless deployment and management of local large language model backends, frontends, and services with integrated support for the Model Context Protocol ecosystem.
mattzcarey/shippie
Shippie is an AI-powered code review agent that integrates Large Language Models into CI/CD pipelines and functions as a Model Context Protocol client for enhanced integration with external tools.