Best Protocol AI Skills & MCP Servers

Model Context Protocol (MCP) server for Kubb, enabling AI assistants to generate code from OpenAPI specifications.

Read-only MCP server for UniFi Network controllers

MCP server for screenpipe - search your screen recordings and audio transcriptions

Avallon API MCP server - generated from OpenAPI

Intelligent file reading — multiple modes to minimize token usage.

File and repo structure outline — list exported symbols and directory trees without reading full content.

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.

MCP tool definitions for SmartyTalent API

MCP server for cross-repo feature development with Super CLI

An MCP server that lets AI agents (Claude, Cursor, etc.) reach you on any channel — desktop, Telegram, SMS, email — with two-way ask/reply, real-time inbox push, Do Not Disturb, idle gating, multi-session routing, and a one-page web UI for setup. Zero con

A Model Context Protocol (MCP) server for Ragie

Generic MCP shell for agent-driven remote Chrome control through cdp-bridge and canonical cdper packages

MCP server for Software Analysis and Design course materials at BGU

MCP server for EUI Angular component library using Compodoc documentation

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

MCP server for AI image generation and manipulation

MCP client for discovering and exercising resources, tools, prompts, and completions over stdio or OAuth-protected HTTP. Ships with a CLI, an interactive REPL, and a web dashboard served by `mcp-inspector serve`.

Convert between formats and units — unit conversion, encoding, format transformation, naming conventions.

A Linear MCP server for interacting with Linear's API

List directory contents — entries, tree, glob, find.

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

Format data into various output formats — pretty JSON, YAML, markdown, ASCII tables.