Best Architecture AI Skills & MCP Servers

Codai Better Database - High-Performance Vector Memory System with HPKV-inspired architecture and MCP server

Project-level understanding without reading all files — detect framework, language, conventions, and architecture.

Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI platform reads (Claude Code, Codex, Copilot, Cursor, Warp, OpenClaw, and 6 more) so one source of truth works across 10 platfo

MCP proxy for Pharaoh — maps codebases into queryable knowledge graphs for AI agents. Enables Claude Code in headless environments (VPS, SSH, CI) via device flow auth.

MCP server that gives AI agents (Claude, Cursor, Copilot) deep understanding of your codebase patterns, conventions, and architecture. Query patterns, security boundaries, call graphs in real-time.

A production-grade MCP server for IBM i

Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.

Automated ADR (Architecture Decision Records) for Claude Code - MCP server with SQL-backed decision repository

TypeScript MCP server boilerplate with STDIO and HTTP transport support, CLI tools, and extensible architecture

Your Claude Code sessions don't have to start from scratch anymore — SpecMem gives your AI real memory. It won't forget your conversations, your code, or your architecture decisions between sessions. That's the whole point. Semantic code indexing that act

Local-first AI-powered codebase analysis tool for stdio or HTTP transports using environment-supplied provider credentials.

CLI + MCP sentinel for engineering standards — SOLID, testing, architecture, CI/CD — auto-tailored to your stack. Minimal MCP footprint (~200 tokens) via CLI-first design.

MCP server — copilot de estrutura para vibe coders

Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear

MCP server that auto-generates Architecture Decision Records from Claude Code conversations using Claude Opus

ctxloom — The Universal Code Context Engine. A local-first MCP server providing intelligent code context via hybrid Vector + AST + Graph search with Skeletonization (92% token reduction).

Comprehensive Model Context Protocol server for WordPress management with composition-based architecture, 59 tools, SEO toolkit, performance monitoring, intelligent caching, and production-ready authentication

Structured code review — analyze code quality, security, architecture patterns, compare versions.

Full project audit workflow — code quality review, security scan, architecture analysis, and metrics report.

MCP server for software architecture design and planning

Graph clustering — detect communities, explain groupings, identify architecture layers.

CodeAtlas MCP server — 40 tools + 8 resources that expose live codebase architecture (routes, sequences, diffs, impact analysis, architecture violations, read-only SQL access) and AI-driven code review (per-entry-point review, evidence-gated findings, cus

Model Context Protocol server for static analysis of Go codebases with shadow SQLite indexing, background sync, call graphs, import graphs, interface topology, struct lifecycle, endpoints, maintainability metrics, and repo-aware config.

The Autonomous Brain for your codebase — compiled architectural knowledge for AI-assisted development.