Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
Flux159/mcp-chat
mcp-chat is an open source command line and web chat client whose purpose is to exercise MCP servers and agents. It is distributed on npm and normally run through npx, so no installation step is needed. Pointing it at a server is a single flag: --server takes the command line that launches any MCP server written in JavaScript or Python or packaged as Docker, and the client then opens an interactive prompt in which the user converses with a model while the server tools are available. Alternatively --config reads an existing claude_desktop_config.json on macOS or Windows, reusing whatever servers are already configured there. The client requires an ANTHROPIC_API_KEY, either exported or in a .env file, because only Anthropic models are supported at present; the model is selected with -m. A single prompt can be sent non-interactively with -p, which runs the prompt, prints the response on stdout and exits, making the tool usable in scripts and continuous integration. The --system flag replaces the system prompt. A --web flag starts a browser interface where chats can be created and MCP servers configured dynamically through the UI rather than on the command line. Chat history and settings are saved under ~/.mcpchat/chats for both modes, and previously used commands are stored in ~/.mcpchat/history so they can be recalled. For server developers the notable feature is that tool call arguments and their output are displayed inline in the conversation, which turns the chat into a debugging surface; local builds of a Node or Python server can be passed directly by path or executed through node or bun. Environment variables are forwarded to the spawned server process, though the README notes this is not part of the MCP specification and other clients may not do it.
https://github.com/Flux159/mcp-chat
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.