tuui and diy-tools-mcp
These are complements: the desktop MCP client provides the interface for discovering and executing tools, while the dynamic tool server enables users to expand the available tool set at runtime within that same MCP ecosystem.
About tuui
AI-QL/tuui
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
Supports full MCP specification including tools, prompts, resources, sampling, and discovery via the MCP registry, with bundled .mcpb extension support for modular server composition. Built on Vue 3 with Electron for cross-platform desktop deployment, featuring dynamic LLM endpoint configuration that accepts multiple vendor APIs (OpenAI, Claude, Qwen, DeepInfra) through JSON-based server manifests and optional remote MCP server proxying via Cloudflare's mcp-remote protocol.
About diy-tools-mcp
hesreallyhim/diy-tools-mcp
An MCP server that allows users to dynamically add custom tools/functions at runtime
Supports multi-language function execution (Python, JavaScript, Bash, Ruby, TypeScript) with file-based or inline code definitions, automatic JSON Schema validation, and persistent tool storage. Built on the Model Context Protocol with timeout protection and comprehensive security checks for sandbox isolation. Integrates seamlessly with Claude and other MCP clients through stdio transport, enabling runtime tool extension without server restarts.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work