Best MCP AI Skills & MCP Servers

UniFi semantic analysis MCP server — fleet health, anomaly detection, cross-site analytics on top of Cloud API

65+ real GitHub Actions errors, queryable by agents. CLI + MCP server + Copilot skills + error database.

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

Extended Google Classroom MCP server via gogcli — auth + full Classroom support

Skilder Runtime - NodeJS processes for edge execution connected to backend orchestrator via NATS

A weather MCP server for Cursor

Extended Google Drive MCP server via gogcli — auth + full Drive support (upload/download/permissions/comments/shared drives)

Interactive CLI for Undisk MCP — undo-first versioned file storage for AI agents

Pack files into a compressed context bundle — reduce token usage by extracting only signatures, maps, or full content.

Local Markdown documentation hub with a built-in MCP server — coding agents create ADRs, draw diagrams and detect drift while you code.

Model Context Protocol server for MDMagic — convert Markdown to professional DOCX, PDF, and HTML using MDMagic templates.

Local-first MCP server for Claude/Codex project wiki and graph workflows

Task dispatch queue — send tasks, manage queue, cancel, check status for multi-step workflows.

MCP server that gives AI assistants (Claude, Cursor, Continue) full control of your Rustrak error tracking

Ricord — persistent memory + repo knowledge graph for AI coding assistants. Ships an MCP server (`ricord-mcp`) and a repo ingestion CLI (`ricord init`).

Burningbros BBPM MCP — Model Context Protocol server exposing the BB Project Management API to Claude. Create issues, assign tasks, comment, and query the board from a chat prompt.

Sandboxed code execution — run JavaScript/TypeScript snippets in an isolated VM context.

An MCP server to debug Node.js at runtime

AI team coordination — loads dispatch, parallel, debate, review, agent for multi-agent orchestration.

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.

Inline, extract, and move refactoring — inline variables/functions, extract code to new functions, move between files.

MCP Server for UNO Online — let AI clients play UNO via MCP tools

Fast Markdown linter and formatter with localized CLI help and version aliases.

Structured decision-making — define options, analyze tradeoffs, recommend, and record decisions.