121,304 servers from the official registry, GitHub and npm. Filter by category, transport and language.
Compresses AI coding agent context to cut token costs, measure per-agent savings, and share a local knowledge graph across 16 CLI clients.
$claude mcp add token-optimizer-mcp -- npx -y @ooples/token-optimizer-mcp
Connects advertising, commerce, analytics, and finance tools to provide AI assistants with normalized data and statistical analysis capabilities.
$claude mcp add autario-mcp -- npx -y autario-mcp
Lets an AI coding client query Cursor CCE for source-anchored project context and optionally run a scoped Cursor Agent task.
Provides AI agents with long-term, self-learning memory through a context engine that manages project-specific vaults and team permissions.
$claude mcp add memory-mcp -- npx -y @ragionex/memory-mcp
Provides an automated Chrome-based QA engine that audits web applications for accessibility, security, performance, and visual regressions.
$claude mcp add argus -- npx -y argusqa-os
Provides structured Saju and BaZi astrology data, including Four Pillars charts, luck cycles, and classical texts, for AI agents.
$claude mcp add --transport http cafe-mcp https://mcp.24plus.ai.kr/mcp
Provides a semantic memory infrastructure for AI agents to save decisions, context, and sources with quality-gated writes and conflict tracking.
$claude mcp add --transport http cortex-connector https://skynetlab-cortex-saas-mcp.cortex-320.workers.dev/mcp
Provides a persistent multi-agent memory and coordination engine that lets AI agents store, retrieve, and share contextual knowledge using SQLite.
Provides a local-first personality engine that enables AI agents to maintain persistent, evolving personas across sessions and context compressions.
$claude mcp add stemem -- npx -y stemem
Provides a local-first memory engine for AI agents to store and retrieve facts, decisions, and concepts using hybrid semantic and full-text search.
A Model Context Protocol (MCP) server that enables AI assistants to perform web searches using SearXNG, a privacy-respecting metasearch engine.
The AI-native 3D game engine where agents code, build, and test games live on the canvas. Powered by React Three Fiber, WebGL, and Model Context Protocol (MCP). Works everywhere from mobile browsers to native desktop. �
A Model Context Protocol (MCP) server that enables AI assistants to interact with the Godot game engine.
A Model Context Protocol (MCP) server for seamless integration with AivisSpeech text-to-speech engine. This project enables AI assistants and applications to convert text to natural-sounding Japanese speech with customiz
The Universal Behavioral Contract & Context Engine that turns any AI coding agent into a disciplined senior engineer — eliminating regressions, hallucinations, and unwanted pushes.
Context filter + AI SBOM + retrieval engine for agents working against corpora larger than any model's context window. Local-first, markdown-native, MCP-ready. Haiku 4.5 reaches 98.3% of Opus quality at 12× lower co
Enterprise-grade multi-agent AI system (CrewAI + AutoGen + MCP) that automates B2B lead qualification, RAG-based context retrieval, multi-dimensional compatibility scoring, and personalized sales outreach—synced directly