A curated list of the best MCP Servers, featuring top solutions, libraries, tools, and more. -
AWS MCP Server Configurations for different operating systems
AI-powered E2E testing MCP server. Point at a URL — AI generates test scenarios, runs Playwright tests, and self-heals failures automatically. Works on Canvas and Flutter Web apps.
Enables LLM-powered agents to generate, execute, and analyze Alloy modeling language code for software modeling and formal verification. Provides tools to run Alloy models, access documentation and examples, and generate models from system descriptions.
AWX Model Context Protocol (MCP) integration for enhanced automation workflows. This repository provides a structured approach to managing AWX models efficiently.
Paid MCP server that evaluates typography accessibility beyond what axe and Lighthouse catch. $0.05 USDC per evaluation via x402 on Base mainnet.
Open-source TypeScript/Python → Swift compiler for Apple platforms. AI agents write 5–15× less code to generate App Intents, SwiftUI views, WidgetKit widgets, and full apps. MCP server with 6 tools for scaffolding, compiling, validating, and browsing templates.
Persistent decision memory and contradiction detection for AI coding agents. Enforces architectural consistency across sessions — the agent cannot code until it loads prior decisions. Human resolves conflicts on a dashboard or in chat.
Integrates the AXLE (Axiom Lean Engine) CLI with AI assistants to provide comprehensive tools for Lean 4 proof engineering. It enables users to validate, repair, and transform Lean theorems through a remote API without requiring a local Lean installation.
Persistent project memory + architectural decisions + pre-execution safety hooks for Claude Code. Local-only storage, multi-repo workspace, automatic knowledge extraction via background auditor.
An MCP server for building Lean4 code, and automated theorem proving
A Model Context Protocol service registry and connector framework that enables seamless integration with multiple services and models through a standardized API interface. Provides an extensible architecture for custom service adapters, API integrations, and model registries.
Provides AI assistants with tools to query and explore the Azgaarnoth D\&D world repository, including searching content, retrieving stat blocks, spells, and browsing categories like races, classes, nations, and creatures across ~4,200 markdown files.
Remote Azure DevOps MCP Server
A Model Context Protocol server that provides Azure Java SDK documentation to AI assistants, allowing them to access readme files with introductions, key concepts, and code samples.
Links to samples, tools, and resources for building and integrating Model Context Protocol (MCP) servers on Azure using multiple languages
Enables interaction with AIApp BaaS authentication system through keyword-based document search and automatic generation of framework-specific client code. Supports React, Next.js, Vue, and Vanilla JS with TypeScript integration and automatic project ID injection.
Executes development tasks by bridging Claude Desktop with Claude Code CLI, enabling automated code generation and task completion in specified working directories.
Persistent, cross-session task management for Claude Code. 24 MCP tools for tasks, projects, dependencies, and docs. 7 skills for planning, standups, and handoffs. Event-sourced storage with per-project isolation.
An MCP server that gives AI agents structured read/write access to a story-based project backlog. Agents can list stories, read content, update status, and append notes — all backed by plain markdown files that live inside your project repository. There is no shared server. The backlog files live in your repo under requirements/, committed and versioned alongside your code





