QueryWeaver is an open - source Text2SQL tool that converts natural language questions into SQL queries through graph - driven schema understanding, supporting REST API and MCP protocol.

DINO-X MCP is a project that enables large language models to perform fine-grained object detection and image understanding through DINO-X and Grounding DINO 1.6 API. It can achieve precise object positioning, counting, attribute analysis, and scene understanding, and supports natural language-driven visual tasks and workflow integration.

MCP-Memos is a memo tool based on the MCP protocol, designed specifically for developers. It supports quick recording and retrieval of text information without switching applications. It uses large language models to provide powerful fuzzy search capabilities, including semantic understanding, context awareness, and natural language query functions.

This project is a document processing server based on the Model Context Protocol (MCP) standard. By building a vector database and an MCP interface, it enables AI assistants to access external document resources and break through the knowledge limitations of large language models. The project includes two major components: a document processing pipeline and an MCP server. It supports multiple embedding models and file formats and can be applied to scenarios such as querying the latest technical documents and understanding private code libraries.

Code Graph RAG MCP is an advanced model context protocol server that provides 13 professional tools for code understanding, relationship mapping, and semantic search through intelligent graph representation and multi - language code analysis capabilities.

A code analysis server based on the MCP protocol that helps AI models understand and analyze codebases through natural language conversations, providing lightweight code exploration and understanding capabilities.

The MCP Code Indexer is an intelligent code retrieval tool designed specifically for large AI language models. It improves the efficiency and accuracy of code processing through semantic understanding and vectorized indexing, supporting functions such as code analysis, quality assessment, and dependency management.

An AI research assistant tool based on Node.js and the Gemini API. It uses Firecrawl for web data scraping, leverages the Gemini large - model for in - depth language understanding and report generation, supports iterative in - depth research, and can be integrated with the MCP protocol.

Nabu and Nisaba are research prototype toolkits used to enhance the code understanding and development efficiency of LLM agents. Nabu, as an MCP server, provides code semantic search and structure analysis functions, supporting multiple programming languages; Nisaba provides workspace management capabilities for Claude Code through proxy injection and a TUI interface, helping agents manage context usage autonomously.