Best Code AI Skills & MCP Servers

Mneme — the memory layer for your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.

Precise code editing — replace function bodies, insert before/after, safe delete with dependency check.

Code modification toolkit — loads symbol, rename, codeedit, inline, textsearch for automated refactoring.

Complete codebase intelligence — loads treesitter, symbol, outline, callgraph, depgraph, refs.

Hud MCP

Powerful MCP server with Tree-sitter WASM parsers for 100% AST accuracy. Zero native dependencies. Production-ready with persistent caching, structured logging, file watching, fuzzy search, rate limiting, file locking, and ReDoS protection. Supports TypeS

Knowledge infrastructure SDK for AI agents - universal references, multi-tier caching, storage abstraction, and sync

Call graph analysis — callers, callees, call chains.

Your AI forgets everything between sessions. cachly fixes that permanently. Persistent memory + causal root-cause analysis for Claude Code, Cursor, Copilot & Windsurf. Learns from every bug fix, git commit, and CI run automatically. Arrives pre-briefed. P

MCP server for Alexandria — 171 expert AI agents across 22 teams, accessible from Claude Desktop and Claude Code

Code intelligence MCP server. Indexes your repository into a queryable call graph for AI coding agents.

Model Context Protocol server for the PropLine player props betting odds API. Exposes live odds, prop resolution, cross-book +EV, scores, and box-score stats as tool calls for Claude Desktop, Claude Code, and any MCP-compatible client.

MCP server for LaunchRoad — gives any MCP-compatible AI coding assistant (Claude Code, Cursor, VS Code, ChatGPT Desktop) live read/write access to your team's shared brain.

MCP server for CostHawk - AI API cost monitoring and optimization with Claude Code tracking

Local dashboard to sync Claude Code, Cursor, Codex, Gemini CLI, and Qwen Code rules, MCP servers, and skills.

MCP server exposing Mushi Mushi reports to coding agents

Model Context Protocol server for the Oriva public API. Exposes all 46 public endpoints as MCP tools for use in Claude Code, Cursor, Continue, and Claude Desktop.

Autonomous demo agent for SaaS products — MCP server for Claude Code, Claude Desktop, Cursor, Windsurf, and any MCP-compatible agent. Discovers, integrates, and runs AI-guided product demos. Starts in onboarding mode with no API key so the calling agent c

Create a Context Hub — a personal AI context layer shared across any MCP client (Claude.ai, Claude Code, Claude App, ChatGPT, Perplexity, Cursor, and more). One command to scaffold, deploy, and connect.

SaaSboard MCP server — query and manage projects, initiatives, tasks, decisions, docs and agent sessions from AI agents (Claude Code, Cursor, etc.)

CLI/MCP tool providing TypeScript code intelligence via the TypeScript Language Service. Analyze exports, imports, resolve symbols, and check type errors.

Local memory layer for AI agents — coding assistants over MCP, game NPCs over REST

MCP server for Claude Code, Cursor, and Windsurf — both teaches Ellivate-shaped patterns up-front and exposes action tools (doctor, publish, list-apps, etc.) the AI uses to actually translate and ship projects.

AsyncAPI MCP server — Model Context Protocol server for working with AsyncAPI: parse and validate documents, list templates, and generate code and docs (via @asyncapi/parser and @asyncapi/generator) for any MCP-compatible client