Cursor インストールガイド
開発者向け MCP サーバーとよく使われる AI コードエディタ。
MCP Servers
Model Context Protocol (MCP) server implementation for Autodesk Maya
A Model Context Protocol (MCP) server which provides AI assistants with seamless access to SmartBear's suite of testing and monitoring tools, including BearQ, BugSnag, Reflect, Swagger, PactFlow,...
MCP (Model Context Protocol) server to manage documents and perform searches using Needle through Claude's Desktop Application.
A high-performance for , enabling AI assistants like , , and other MCP clients to interact seamlessly with your Metabase instance.
https://youtu.be/K0t6MRyIqZU?si=Mz4d65DcAD3i2YbO
Connect AI agents to your ThingsBoard IoT platform via Model Context Protocol (MCP). Query devices, manage entities, analyze telemetry, and automate operations — all through natural language.
A Model Context Protocol (MCP) server that automates optimization and analysis using Optuna.
Manage variable names, constants, and standard terminology per project systematically, and integrate with Cursor IDE to help LLMs use consistent naming conventions.
A Model Context Protocol (MCP) server that provides C++ code analysis capabilities through clangd LSP integration.
The Kubeflow MCP Server exposes Kubeflow Training operations as Model Context Protocol tools, enabling AI agents (Claude, Cursor, Claude Code, or any custom agents etc.
A Model Context Protocol (MCP) server implementation that connects Large Language Models (LLMs) to the GeoServer REST API, enabling AI assistants to interact with geospatial data and services.
The implementation of Model Context Protocol (MCP) server for VictoriaLogs.
Agent Skills
A custom Claude Code skill: a strict for Python, Bash, Google Apps Script, JavaScript, and Swift/Apple platforms.
xhs-account-teardown
A Copilot CLI skill that analyzes your repository and generates the configuration files AI agents need to contribute correctly.
Practices, protocols, and skills for AI-driven software development
专为 优化的 Codex skill，大幅降低 token 消耗并提升前缀缓存命中率。
AI Unified Process (AIUP) is a requirements-first workflow for taking software from a product vision to reviewed specifications, implementation, and traceable tests.
23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex desktop edition tuned for Astra. Source for clickai.dev.
Agent-native persistent knowledge management — compile knowledge once, query forever.
MCP server, CLI, and agent skills for Pipefy.
My Codex Skills
Lightweight AI assistant framework in Rust with pluggable LLM providers (Ollama, llama.cpp, vLLM), built-in tool calling, agent skills, and customizable system prompts.
micro-agent orchestrator for local agents