Best MCP Servers

Pantheon-Security/medusa

Medusa is an AI-first security scanner featuring over 40,000 detection patterns to identify vulnerabilities in AI/ML applications, LLM agents, and codebases. It includes specialized capabilities for detecting repository poisoning, analyzing remote GitHub repositories, and scanning chat or shell histories for leaked API keys.

headroomlabs-ai/headroom

Headroom is a local context compression layer that reduces LLM token consumption by 60% to 95% for JSON and 15% to 20% for coding agents without losing accuracy. It operates as a library, local proxy, MCP server, and direct agent wrapper to optimize both incoming prompts and outgoing model responses.

Deuz-AI/Deuz-SDK

Deuz-SDK is a zero-dependency TypeScript runtime designed for production-grade AI agents, offering advanced durability, state compaction, and memory management.

Vishisht16/Humane-Proxy

Humane-Proxy is a lightweight AI safety middleware designed to intercept and filter user messages for self-harm ideation or criminal intent before they reach an upstream LLM. It combines heuristic keyword matching, semantic embeddings, and reasoning models to provide real-time risk evaluation, empathetic user care, and operator alerts.

Eronred/aso-skills

A comprehensive collection of AI agent skills specialized in App Store Optimization (ASO) and mobile app growth, powered by real App Store data via the Appeeky API.

btopn/OpenInsider-MCP

OpenInsider-MCP is a Model Context Protocol server that supplies LLMs with free-data investment-research signals including insider trades, SEC filings, short data, and live quotes. It acts as a pure data layer without editorialization or recommendation features.

DeusData/codebase-memory-mcp

An ultra-fast code intelligence engine that builds persistent knowledge graphs using tree-sitter and hybrid LSP for AI coding agents.

Paca-AI/paca

Paca is an open-source, self-hosted project management platform that integrates AI agents as first-class Scrum teammates alongside humans. It features a unified Scrumban board, BDD collaboration, and an extendable WebAssembly plugin architecture.

stripe/ai

This skill acts as a guided advisor for configuring Stripe Connect integrations, analyzing user business models, and recommending appropriate payment flows, charge patterns, and account structures.

Graphify-Labs/graphify

Graphify maps entire project codebases, documentation, and media into an interactive local knowledge graph, enabling AI assistants to query the graph instead of grepping raw files.

microsoft/DebugMCP

DebugMCP is a VS Code extension that integrates an MCP server, allowing AI coding agents to control the built-in debugger via the Debug Adapter Protocol.

MicrosoftDocs/mcp

An official Microsoft Learn Model Context Protocol (MCP) server and agent skill suite that connects AI assistants directly to current Microsoft documentation and code samples.

Azure-Samples/azure-ai-travel-agents

This repository provides a modular multi-agent travel planning system with three standalone orchestration options: LangChain.js, LlamaIndex.TS, and the Microsoft Agent Framework. It uses Model Context Protocol (MCP) microservices to coordinate specialized agents for customer queries, destination recommendations, and itinerary planning.

ThreeMoonsLab/agents-shipgate

Agents Shipgate is a deterministic merge gate for AI-generated agent capability changes, analyzing tool sources and configurations locally without agent execution or network calls.

Sibyl-Labs/Sibyl-Memory

Sibyl-Memory is a local-first, SQLite-backed agentic memory infrastructure that uses a five-tier hierarchical schema and FTS5 search without relying on vector databases or embedding models.

zhangxiangliang/stock-api

Fetches real-time quotes, historical K-line charts, and symbol lookups for Chinese A-shares, Hong Kong, and US markets with automatic provider fallback.

TeleAI-UAGI/telemem

TeleMem is a high-performance, drop-in memory management layer for AI agents offering character-profiled memory and a complete multimodal video understanding pipeline. It serves as an optimized, local-first alternative to Mem0 with enhanced accuracy and lower token overhead.

jau123/MeiGen-AI-Design-MCP

An open-source Model Context Protocol server that integrates multi-provider AI image and video generation into major AI assistants.

flowing-abyss/obsidian-hybrid-search

Obsidian Hybrid Search provides local hybrid retrieval combining semantic vectors, BM25 full-text, and fuzzy matching for Obsidian vaults. It exposes this engine through a CLI, MCP server, and native Obsidian plugin.

zosmaai/pi-llm-wiki

Implement Andrej Karpathy's LLM Wiki pattern as a self-maintaining, Obsidian-compatible knowledge base extension for AI coding agents. It compiles raw sources into a structured, multi-layered vault that compounds over time.

daniel3303/Equibles

Equibles is a self-hosted, open-source financial data MCP server that provides AI agents with direct access to SEC filings, institutional holdings, insider trades, and economic indicators. It functions as an open-source Bloomberg Terminal alternative built for programmatic querying.

marvkr/better-design

Better Design is an MCP server and design system registry that equips AI coding agents with production-ready design tokens, component styles, and accessibility review rules.

CodeAbra/iai-personal-memory-engine

iai-personal-memory-engine (iai-pme) is a local, ambient personal memory engine for AI coding assistants that captures interactions verbatim and serves context via the Model Context Protocol (MCP).

beizhu-1209/AIHelms

AIHelms is an enterprise-grade AI resource management platform designed to help organizations control costs, track usage metrics, and securely manage AI assets and API access.

diegosouzapw/OmniRoute

OmniRoute is a unified AI proxy and router supporting hundreds of LLM providers with automatic fallback, advanced routing strategies, and built-in resilience mechanics.