morluto/rea
REA (Reverse Engineer Anything) is an MCP server and CLI that let AI coding agents reverse-engineer native binaries, Electron/JavaScript apps, .NET assemblies and websites, with evidence for each finding.
Awesome AI Agents › MCP Server Framework
xerj-org/xerj
XERJ is a local-first search engine and MCP server built for AI coding agents. A single Rust binary indexes a project's code, documentation, specifications, logs, JSONL/CSV data and PDFs, then exposes that index through an Elasticsearch-compatible API as well as an MCP server endpoint. It supports BM25 full-text search, vector search, hybrid search, code-aware search and a persistent agent memory layer, letting an agent look up relevant context instead of loading entire files or relying only on the model's context window. The project is positioned as a drop-in retrieval backend for agent harnesses such as Claude Code and Cursor, and for any other MCP-compatible client: the agent calls the MCP tool, XERJ returns cited answers drawn from the indexed corpus, and the agent continues its task with grounded context. Indexing is automatic and zero-config once pointed at a directory, so a repository or document set becomes searchable without a separate database to provision or manage. The maintainers also ship "Corpus Hub" packs, which are prebuilt indexes of external reference material that can be attached alongside a project's own index. Being a single local binary with no required external services makes it easy to run alongside an existing agent workflow on a developer machine or in CI, and the project reports meaningfully fewer tokens spent on reference lookups when agents use XERJ instead of re-reading files directly. It targets developers and teams building or using AI coding agents who need a fast, self-hosted way to give those agents structured, searchable memory over a codebase and its surrounding documentation.
https://github.com/xerj-org/xerj
Also in MCP Server Framework
thedaviddias/Front-End-Checklist
Front-End Checklist is an open-source quality system for modern web development, offering comprehensive best practices for humans and AI agents.
trycua/cua
c/ua is a high-performance framework that enables AI agents to control full macOS and Linux operating systems within secure, lightweight virtual containers on Apple Silicon Macs, supporting complex autonomous workflows and LLM integration.
PrefectHQ/fastmcp
FastMCP offers a Pythonic framework for building Model Context Protocol (MCP) servers and clients, facilitating structured communication for AI agents and models.
pascalorg/editor
Local-first 3D building editor built with React Three Fiber and WebGPU that exposes an MCP service so AI agents can create and edit 3D scenes.
nukeop/nuclear
Nuclear is a free, open-source, ad-free music player for Windows, macOS, and Linux, featuring streaming from various sources, playlist management, a powerful plugin system, and integration with AI ...
googleapis/mcp-toolbox
MCP Toolbox for Databases is an open-source server that connects AI agents and applications to enterprise databases using the Model Context Protocol (MCP).
apify/apify-mcp-server
Model Context Protocol server that exposes thousands of Apify Actors as tools, letting AI agents scrape social media, search engines, maps and e-commerce sites over hosted HTTP or local stdio.