Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
adhikasp/mcp-client-cli
The project "mcp-client-cli" is a command-line interface tool designed to interact with Model Context Protocol (MCP) compatible servers and run large language model (LLM) prompts directly from the terminal. It serves as a simple and efficient alternative client to other MCP clients like Claude Desktop, enabling users to leverage various LLM providers such as OpenAI, Groq, or local LLM models through llama.cpp. The tool allows users to configure their LLM and MCP servers via a JSON configuration file, supporting multiple MCP servers with customizable commands, arguments, environment variables, and tool confirmation settings. Users can install the tool via pip and set up their configuration file to specify system prompts, LLM provider details, API keys, and MCP server commands. The CLI supports basic usage where users can input prompts directly or pipe input from other commands or files. It also supports multimodal input, allowing users to pipe image files for analysis by multimodal LLMs. The tool includes features such as predefined prompt templates for common tasks like reviewing git changes, generating commit messages, or summarizing YouTube videos. It supports triggering tools on MCP servers with optional user confirmation for tool calls, and users can bypass confirmations or intermediate messages with command-line flags for scripting purposes. Additional functionalities include continuation of conversations with a prefix, clipboard support for text and images across different operating systems, and various command-line options to list tools, prompts, disable tools, force refresh caches, output raw text, show user memories, or override the LLM model. Overall, mcp-client-cli provides a versatile and user-friendly command-line interface for interacting with MCP servers and LLMs, facilitating seamless integration of AI capabilities into terminal workflows for software engineers and other users.
https://github.com/adhikasp/mcp-client-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.