Hmbown/CodeWhale
An open-source terminal coding agent written in Rust, with MCP support, multi-model routing and multi-agent orchestration.
theailanguage/mcp_client
This repository collects four command-line MCP client implementations in Python, each paired with a video tutorial, that connect a Google Gemini model to MCP servers. The first script is a minimal stdio client with no framework dependency. The second wraps the same stdio transport in LangChain. The third adds configuration file support so one client can connect to several MCP servers at once, reading the server list from a JSON file. The fourth speaks the SSE transport and can target a local or remote server URL. Each is launched through uv with a single argument: a path to a server script for the stdio variants, a path to a configuration file for the multi-server variant, and a server URL for the SSE variant. The comparison table in the README makes the differences explicit across the LangChain, configuration support and transport columns, so a reader can pick the smallest client that covers their case. The execution flow is the same in every variant: the user types a prompt such as a request to create a file, the prompt goes to Gemini along with the tool definitions advertised by the connected server, Gemini selects a tool, the client executes that call against the server, and the result is returned to the model, with conversation context maintained where supported. The project layout is flat, with the four client scripts, a dotenv file holding the API key, a requirements list and a licence at the top level. Readers who want servers to point these clients at are directed to the reference MCP servers repository. The author does not accept external code contributions to keep copyright simple, but invites issues, forks and documentation suggestions.
https://github.com/theailanguage/mcp_client
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.