Best AI AI Skills & MCP Servers

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

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

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

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.

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

MCP server for Workjournal — exposes tools for creating, searching, and listing journal entries from any MCP-compatible AI agent.

File access heatmap — track read/write patterns, detect hot and cold files.

Track and report token savings — compare FocusMCP usage vs naive full-read, trend over time, ROI.

Schema-driven Node.js backend that auto-generates REST + GraphQL + MCP from one schema file per resource. Built for AI agents.

Symbol lookup in source files — find, get, bulk, body.

Self-hosted LLM gateway and tier-routing proxy for Claude Code, Cursor, and Codex. Routes across Ollama, AWS Bedrock, OpenRouter, Databricks, Azure OpenAI, llama.cpp, and LM Studio with prompt caching, MCP tools, and 60-80% cost savings.

agentry MCP server — the canonical entry point. Drop it into Claude Code, Cursor or any MCP-compatible AI and your assistant can read your app's errors, analytics and deploys directly.

React hooks adapter for Tesseron. useTesseronAction, useTesseronResource.

MCP server for TensorFeed.ai - AI news, service status, model pricing, signed decision verdicts, time series, model comparison, webhook watches, and a discovery tool for the full TensorFeed data catalog, for AI agents

Semantic search using TF-IDF vector space — cosine similarity, intent matching, document similarity.

Task management for multi-agent workflows — create tasks, assign to agents, track status, mark complete.

MooseRunner boosts PlayMode testing with Hot Reload, MCP for AIs, timescale control, and Task support. It enables rapid iteration, auto test reruns, full documentation and dedicated support.

Node.js MCP server for GitLab code review operations with AI integration support

MCP server for Dynamsoft SDKs - Capture Vision, Barcode Reader (Mobile/Python/Web), Dynamic Web TWAIN, and Document Viewer. Provides documentation, code snippets, and API guidance.

Parallel execution coordination — run tasks concurrently, collect results, merge outputs, handle timeouts.

A comprehensive Model Context Protocol (MCP) server that provides web performance auditing, accessibility testing, SEO analysis, security assessment, and Core Web Vitals monitoring using Google Lighthouse. Enables LLMs and AI agents to perform detailed we

MCP server for MarginFront. Lets AI agents (Claude, Cursor, Copilot) record usage events, query revenue / cost / MRR analytics, manage customers + subscriptions + pricing plans, browse the supported-services catalog, generate and email invoices, and manag

MCP Lite v0.4: manual-trigger MCP server (12 tools: 7 codex-side + 5 claude-side wrapping agent-collab.ps1 + Git + .agent/) plus collab-watch — a watcher daemon that orchestrates the Claude→Codex→Claude collaboration loop via opt-in auto-execute mode. Req