diy-tools-mcp and tuui
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 diy-tools-mcp
hesreallyhim/diy-tools-mcp
An MCP server that allows users to dynamically add custom tools/functions at runtime
This server helps developers extend the capabilities of AI models like Claude by letting them create and add custom functions or "tools" on the fly. You provide code in various languages (Python, JavaScript, Bash) and a description of its inputs, and the server makes it available to the AI. This is ideal for developers building AI-powered applications who need to integrate custom business logic or external system interactions.
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.
TUUI is a desktop application that acts as a local playground for interacting with various large language models (LLMs). It allows users to bring in their preferred LLM backends, such as ChatGPT or Claude, and manage them all from a single interface. The application takes your prompts and configurations, then orchestrates communication with different AI models, providing responses and enabling advanced features like tool use and custom prompts. It's designed for individuals, developers, and researchers who want direct control over their AI interactions without reliance on third-party accounts.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work