Best Lua AI Skills & MCP Servers

MCP server exposing public instruction workflows as tools, backed by hidden AI agent skills for requirements, orchestration, quality, research, evaluation, governance, resilience, and physics-inspired analysis

Evaluate, simplify, and differentiate mathematical expressions via MCP. STDIO or Streamable HTTP.

MCPLab - Test and evaluate MCP servers with LLMs — run evals, compare agents and launch the MCPLab web app

An MCP server for interacting with Roblox Game Clients (Delta, etc) over WebSocket+HTTP, with a server side decompile pipeline and in game UI.

MCP server discovery tool for AI agents. Searches MCP servers across Official Registry, Glama, and Smithery so your AI can find, evaluate, and install tools on demand.

MCP client for refinancier — Trust Infrastructure for Uncertain Assets. Enterprise valuation, anomaly detection, and value-up recommendations for AI agents.

MCP server that gives Claude real-time stock research — investment thesis, earnings analysis, insider signals, valuation, and bear/bull cases. Plus 20 utility tools.

GitHub Action for evaluating MCP server tool calls using LLM-based scoring

MCP Server for xCOMET translation quality evaluation

A Model Context Protocol (MCP) server that provides searchable access to Garry's Mod Lua API documentation

MCP server that exposes MCPLab evaluation tools — query runs, results, and traces via the Model Context Protocol

Core evaluation engine for MCPLab — agent adapters, MCP client, scenario runner, and result types

HTML report generation for MCPLab evaluation runs

Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p

REPL-sharing MCP server — AI and humans co-drive the same visible terminal. 19 embedded adapters: shells (bash, pwsh, zsh, cmd), language REPLs (Python, Node, Deno, Lua, Racket, CCL/ABCL/SBCL Common Lisp, F# Interactive, jshell, Groovy, SQLite3), and debu

MCP server for markdown plan review — companion to the MD Feedback VS Code extension. AI agents read annotations, mark tasks done, evaluate quality gates, and generate session handoffs. 27 tools for Claude Code, Cursor, and other MCP-compatible clients.

45 specialized judges that evaluate AI-generated code for security, cost, and quality.

Security evals for the AI era. Probes · Targets · Graders · Proof. Confirmed XSS / SQLi / BOLA / prompt-injection / MCP-RCE with reproducible proof attached to every finding.

MCP server for AI agents to evaluate consequences before destructive actions. Analyzes Terraform plans, shell commands, and MCP tool calls.

MCP server for Formulon Excel-compatible formula and workbook evaluation

Bilig WorkPaper API, CLI evaluator, and MCP server for headless spreadsheet formulas in Node.js services and agents.

MCP (Model Context Protocol) server for Roblox Studio integration - enables AI coding agents to interact with Roblox Studio in real-time

The agent eval standard for MCP. Score every agent output for quality, safety, and cost.

MCP server for @agentdance/node-webrtc — lets AI agents discover, evaluate, and get started with the pure-TypeScript WebRTC stack