Best AI Coding AI Skills & MCP Servers

Lint your AI agent context files, MCP server configs, and session data against your actual codebase

MCP server for Decantr — exposes Contract context, typed graph artifacts, and verification evidence to AI coding assistants

Persistent memory for AI coding sessions — captures what agents can't infer from code alone. Works with Copilot, Cursor, Claude, and Windsurf.

Lossless, project-scoped memory for AI coding tools. Durable context across sessions with 56 MCP tools, FTS5 search, conductor orchestrator, loop/watch monitoring, snapshot capture, pre-flight overlap checks, Claude/Codex/OpenCode wrappers, Linear sync, a

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

Developer context continuity system — temporal knowledge graph for AI coding agents via MCP. Inspired by Vannevar Bush's 1945 concept of a machine that remembers everything.

Open-source control plane for AI coding agents: budget caps, verifier gates, rollback evidence, and audit trails.

Local-first project memory for AI coding agents.

MCP server for AI coding tools and agents. Provides semantic codebase context for Cursor, Claude Code, Codex, Copilot, Antigravity, and CLI workflows without requiring full file uploads.

Stop losing team knowledge. Capture your team's engineering decisions and serve them to Claude Code, Cursor, and Windsurf via MCP.

Local-first MCP server that gives AI coding agents a living, browser-viewable project wiki and a project-local memory store, so the agent stays oriented and the human stays in control.

Code intelligence toolkit for AI agents — extract functions, trace call chains, find callers, detect dead code without reading entire files. Works as MCP server, CLI, or agent skill. Supports JS/TS, Python, Go, Rust, Java.

Local-first MCP server that gives AI coding agents a living, browser-viewable project wiki and a project-local memory store, so the agent stays oriented and the human stays in control.

AI-powered MCP server for codebase navigation and LLM prompt optimization

Sync MCP servers, Skills, Agents & Commands across Claude Code, Cursor, OpenCode, Codex. One config, all tools.

Local-first orchestration for coding agents — classify, decompose, dispatch Claude/Codex, and supervise from a dashboard.

Local-first MCP server giving AI coding agents fast, structured, and semantic context over any codebase.

Opt-in UI/UX master skill, CLI, and MCP server for AI coding agents, with accessibility, design-system, UX research, and frontend handoff workflows.

MCP (Model Context Protocol) server that lets AI coding agents like Cursor, Claude Code, Copilot, and Windsurf report task status, post progress updates, flag blockers, and mark work complete on a swarmboard kanban board — natively, with no manual prompti

Cody CLI - AINative Studio's AI-powered coding assistant. Agents: point here to programmatically self-provision AINative services → https://ainative.studio/agent.md

Drop-in optimization toolkit for Claude Code — 15 agents, token savings, safety hooks, UI pipeline

Open-source terminal AI agent. 100+ specialist skills + audit-grade finance infra via @kernel.chat/kbot-finance. Content-addressed envelopes, hash-chained audit log, jurisdiction-aware regulatory verifier. The AI Intelligence Layer never produces the numb

Lurus Code — Agentic Coding CLI

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