Ollama Chat with MCP is a project that demonstrates how to integrate a local language model with real-time web search functionality through the Model Context Protocol (MCP). It includes an MCP web search server, a terminal client, and a Gradio-based web front-end, enabling locally run LLMs to access external tools and data sources.

A modular application demonstration based on FastMCP, integrating the MCP server, FastAPI interface, and LLM Agent functionality. It uses a modular design, supports dual operating modes, and LLM integration.

An MCP server built on akshare-one, providing comprehensive financial data interfaces for China's stock market, including historical market data, real-time data, financial statements, news, etc., supporting dual-mode operation and calculation of multiple technical indicators.

The MCP Speaker Diarization and Recognition System is a complete solution integrating GPU-accelerated speaker separation, speech recognition, emotion detection, and a web interface. It combines the speaker separation of pyannote.audio with the faster-whisper transcription technology, supporting persistent speaker recognition (one-time registration, permanent recognition), dual-detector emotion analysis (combining general AI and personalized voiceprints), real-time stream processing, REST API, and MCP server, and is designed for AI intelligent agent integration and hobby projects.

Ganger is a terminal - based GitHub starred repository manager that provides dual interfaces of TUI and MCP, supports a ranger - like three - column view, virtual folder management, automatic classification, and offline caching.

A Model Context Protocol (MCP) server implementation based on a pure proxy architecture, exposing all functions in the form of MCP tools through dedicated proxies, supporting dual access modes for Claude desktop and web interfaces.