Best You AI Skills & MCP Servers

Skar turns a captured AI agent trace into a committed pytest regression test. MCP server + CLI. Use when a tool-using agent run fails and you want to lock the failure as an executable test.

Access your Obsidian vault from Claude Desktop and other AI tools — MCP server wrapping the official Obsidian CLI with tools, resources, and prompts

Install Tracklution server-side conversion tracking. Add the Tracklution MCP at https://mcp.tracklution.com/mcp and let your AI coding agent finish the install. Protocol: https://www.tracklution.com/agent-install.md

Persistent memory + FTS5 search for Claude Code conversations. MCP server exposes your ~/.claude/projects/ history as queryable memory for any MCP-compatible AI agent.

Local MCP credential broker for coding agents (Claude Code, Codex, Gemini, and any other MCP-stdio client). Values never enter the AI transcript — the agent requests secrets through a schema, a localhost form lets you type them, and they land in Vault, .e

Bring a design specialist to your AI workflow. 12 MCP tools connect v0 to Claude Code, GitHub Copilot, and any MCP-compatible agent — for design consultation, component generation, and iterative refinement. Free during preview.

Tapal — universal mail MCP server. Plug into Claude Desktop, Claude Code, Codex, Gemini CLI, Cursor, Windsurf, Zed, Continue.dev, LangChain, CrewAI, AutoGen — and let any AI agent read, search, draft, organize, and triage your email. Apple Mail today; Out

PR Worlds — the CLI and MCP server that gives your repo coherent, reproducible worlds your agent can open, replay, and inhabit. v0.2 ships the coherence resolver: agents see the plan's confidence, evidence, and explicit unknowns before the world is materi

Compile your Markdown vault into a portable agent memory. One build, every agent: Claude, Codex, Cursor, MCP, llms.txt.

iMessage MCP server — 25 tools for searching, analyzing, and exploring your entire iMessage history on macOS

Model Context Protocol server for Cursor Cloud Agents API - programmatically create, manage, and interact with AI-powered coding agents through MCP stdio transport. Integrate automated code generation, repository management, and agent workflows into your

Drive any Electron app from your AI. MCP server with 93 tools, 4 recipe packages (Slack/Discord/Notion/Linear), security primitives, and a CLI mirror. The testing surface area Tauri structurally cannot match.

The MCP Hub — one config that connects every AI agent (Claude, Cursor, Windsurf, Copilot, Gemini) to every MCP server you register

MCP server for AWS S3 — list buckets, browse objects, upload/download files, and generate presigned URLs from your IDE

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

Persistent project memory for LLMs via MCP. Never re-explain your project again.

dwic — the design auditor for Claude Code. MCP server that audits your design tokens + markup for WCAG contrast failures, mandated-accent drift, and structural gaps, then remembers findings across sessions.

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.

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

MCP server that manages your other MCP servers — wrap, restart, add, remove, and health check from within Claude Code.

Talk to your whole repository. GitHub-native browser editor with AI Panel and voice mode. CLI and MCP Server included.

MCP server for retrieving YouTube video transcripts for Claude Code and other MCP-enabled AI tools

MCP security trust layer. Scan packages, inspect repo MCP dependencies, generate Policy Gate setup, check exposure, and query abuse data.

The runtime security layer for AI agent commerce. Drop-in CLI + MCP server — blocks hallucinated purchases and keeps card credentials out of agent context. It only takes 0.1% of hallucination to drain 100% of your wallet.