Supermemory is an AI-driven memory engine designed to provide contextual knowledge for LLMs by integrating personal data, enabling intelligent management and retrieval of information.

A generative AI support plugin for Unreal Engine that integrates multiple cutting - edge LLM/GenAI model APIs, providing AI integration layer support in game development, including chat and structured output functions for models such as OpenAI, Claude, and Deepseek, and supporting the Model Control Protocol (MCP) to achieve advanced functions such as scene object control and blueprint generation.

cutterMCP is a model context protocol server designed for LLMs for autonomous reverse engineering applications.

Binary Ninja MCP is a plugin and server that enables seamless integration between Binary Ninja and LLM clients, enhancing the reverse - engineering workflow by providing binary analysis functions through the MCP protocol.

Crawl4AI MCP Server is an intelligent information acquisition server based on the MCP protocol, which provides multi - engine search and optimized web content extraction functions for AI systems, and converts web pages into a format suitable for LLM processing.

cutterMCP is a model context protocol server designed for LLM, supporting autonomous reverse engineering applications and integrating the core functional tools of Cutter.

The LocaLLama MCP Server is an intelligent routing service that optimizes costs by dynamically assigning coding tasks to local LLMs or paid APIs. It includes core modules such as cost monitoring, decision engine, API integration, error handling, and performance benchmark testing, and supports integration with multiple tools.

Nano Agent is an experimental small engineering proxy MCP server that supports multi-provider LLM models, used to test and compare the proxy capabilities of cloud and local LLMs in terms of performance, speed, and cost. The project includes a multi-model evaluation system, a nested agent architecture, and a unified tool interface, supporting providers such as OpenAI, Anthropic, and Ollama.

Google Custom Search Engine MCP Server provides search capabilities for LLMs

JADX-MCP-SERVER is a Python server that works with the JADX-AI-MCP plugin, enabling LLM (such as Claude) to analyze decompiled Android APK code in real-time through the MCP protocol, providing reverse engineering functions such as vulnerability detection and code understanding.

BinAssistMCP is an MCP service that connects Binary Ninja with large language models (LLMs), providing more than 40 reverse engineering tools and supporting dual transport protocols and intelligent context management.

This project runs the Ghidra reverse engineering tool in headless mode, extracts binary file analysis data and converts it into JSON format, and provides interactive reverse analysis services for LLMs like Claude through the MCP protocol.

An intelligent search engine that combines LangChain, MCP protocol, RAG technology, and Ollama, supporting web search, information retrieval, and answer generation, with the ability to call local and cloud LLMs.

HTTP API bridging and MCP server implementation for Shogi AI engines, integrating LLM and USI protocol Shogi AI, providing position parsing and move explanation functions.

The Search Fusion MCP Server is a highly available multi-engine search aggregation service that provides intelligent failover, a unified API, and LLM-optimized content processing. It supports 7 search engines such as Google, Serper, and Jina AI, and has advanced functions such as concurrency control, connection pool management, and automatic proxy detection.

GhidraMCP is a model context protocol server designed for LLM, supporting autonomous reverse engineering applications and providing Ghidra's core functional tools.

Anyquery is an SQLite - based SQL query engine that supports SQL queries on files, databases, and various applications (such as Apple Notes, Notion, etc.), and extends functionality through plugins. It also supports connecting LLMs (such as ChatGPT) as a data access interface and can run as a MySQL server.

ghidraMCP is a model context protocol server based on Ghidra that allows LLMs to autonomously reverse engineer applications and provides a tool interface for the core functions of Ghidra.

VectorCode is a code repository indexing tool designed to optimize the prompt construction of large programming language models (LLMs) by indexing and providing code repository information. It supports multiple embedding engines, provides command - line tools and Neovim plugins to help developers more efficiently use project context to improve the quality of model output.