Context7

Boost your AI code assistant with Context7: inject real-time API documentation from OpenAPI specification sources into your coding workflow.

Azure DevOps (ADO)

The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents.

Openweathermcp

# OpenWeatherMap MCP Server [English](README.md) | [中文](README_zh.md) A comprehensive OpenWeatherMap API integration server based on Model Context Protocol (MCP), providing AI assistants with full weather data access capabilities. ## 🌟 Key Features ### Core Weather Functions - **🌡️ Current Weather Query** - Real-time weather data including temperature, humidity, wind speed, pressure, etc. - **📅 Weather Forecast** - 5-day/3-hour interval detailed weather forecasts with trend analysis - **🏭 Air Quality Monitoring** - Real-time air quality index and pollutant concentration data - **🗺️ Weather Maps** - Multi-layer weather map tiles (clouds, precipitation, temperature, etc.) - **⚠️ Weather Alerts** - Government-issued weather warnings and safety advisories - **📊 Historical Weather** - Historical weather data queries and multi-day comparison analysis ### Smart City Name Query - **🧠 Intelligent Fallback** - Automatically handles both Chinese and English city names - **🔄 Auto-Geocoding** - When direct city name query fails, automatically uses geocoding to get coordinates - **🌍 Universal Support** - Works with city names in any language through geocoding API ### Additional Features - **🌍 Geocoding** - Place name to coordinates conversion with fuzzy search support - **📍 Reverse Geocoding** - Coordinates to place name conversion - **🔄 Multi-Unit Support** - Metric, Imperial, and Standard unit systems - **🌐 Multi-Language Support** - Chinese, English, and many other languages ## 📦 Installation ### Prerequisites - Node.js 18.0.0 or higher - OpenWeatherMap API key ### Get API Key 1. Visit [OpenWeatherMap](https://openweathermap.org/api) 2. Register an account and get a free API key 3. Set environment variable: ```bash export OPENWEATHER_API_KEY="your_api_key_here" ``` ### Installation Methods #### Method 1: NPM Global Installation ```bash npm install -g openweather-mcp ``` #### Method 2: Build from Source ```bash git clone https://github.com/QianJue-CN/OpenWeatherMCP.git cd OpenWeatherMCP npm install npm run build ``` ## 🚀 Usage ### Run as MCP Server ```bash # Set API key export OPENWEATHER_API_KEY="your_api_key_here" # Start server npx openweather-mcp ``` ### Configure in Claude Desktop Add to Claude Desktop configuration file: ```json { "mcpServers": { "openweather": { "command": "npx", "args": ["openweather-mcp"], "env": { "OPENWEATHER_API_KEY": "your_api_key_here" } } } } ``` ### Use with Other MCP Clients Any MCP protocol-compatible client can connect to this server. ## 🛠️ Available Tools ### 1. Current Weather Query (`get_current_weather`) Get real-time weather information for specified location. **Parameters:** - `city` (optional): City name, e.g., "Beijing" or "北京" or "Beijing,CN" - `lat` (optional): Latitude (-90 to 90) - `lon` (optional): Longitude (-180 to 180) - `zip` (optional): Postal code, e.g., "10001,US" - `units` (optional): Unit system (metric/imperial/standard) - `lang` (optional): Language code (zh_cn/en/es/fr/de/ja/ko/ru) **Smart City Name Support:** - ✅ "北京" (Chinese) → Automatically works - ✅ "Beijing" (English) → Automatically works - ✅ "上海" (Chinese) → Automatically works - ✅ "Shanghai" (English) → Automatically works **Example:** ```json { "city": "北京", "units": "metric", "lang": "zh_cn" } ``` ### 2. Weather Forecast (`get_weather_forecast`) Get 5-day weather forecast data. **Parameters:** - Location parameters same as above - `cnt` (optional): Number of forecast time points (max 40) **Example:** ```json { "lat": 39.9042, "lon": 116.4074, "cnt": 16, "units": "metric" } ``` ### 3. Air Quality (`get_air_quality`) Get air quality data. **Parameters:** - `lat`: Latitude - `lon`: Longitude - `start` (optional): Start timestamp (for historical data) - `end` (optional): End timestamp (for historical data) ### 4. Weather Maps (`get_weather_map`) Get weather map tiles. **Parameters:** - `layer`: Layer type (clouds_new/precipitation_new/pressure_new/wind_new/temp_new) - `z`: Zoom level (0-10) - `x`: Tile X coordinate - `y`: Tile Y coordinate ### 5. Weather Alerts (`get_weather_alerts`) Get weather warning information. **Parameters:** - `lat`: Latitude - `lon`: Longitude ### 6. Historical Weather (`get_historical_weather`) Query historical weather data. **Parameters:** - `lat`: Latitude - `lon`: Longitude - `dt`: Unix timestamp for query date - `units`: Unit system - `lang`: Language code ### 7. Geocoding (`geocoding`) Get coordinates from place names. **Parameters:** - `q`: Location query string - `limit`: Number of results to return (1-5) ### 8. Reverse Geocoding (`reverse_geocoding`) Get place names from coordinates. **Parameters:** - `lat`: Latitude - `lon`: Longitude - `limit`: Number of results to return (1-5) ## 📝 Usage Examples ### Query Beijing Current Weather ```json { "tool": "get_current_weather", "parameters": { "city": "北京", "units": "metric", "lang": "zh_cn" } } ``` ### Get Shanghai 5-Day Weather Forecast ```json { "tool": "get_weather_forecast", "parameters": { "city": "上海", "units": "metric", "lang": "zh_cn" } } ``` ### Query Air Quality ```json { "tool": "get_air_quality", "parameters": { "lat": 39.9042, "lon": 116.4074 } } ``` ## 🌍 How Smart City Name Query Works 1. **Direct Query**: First attempts to query weather using the provided city name directly 2. **Auto Fallback**: If direct query fails (404 error), automatically triggers geocoding 3. **Coordinate Conversion**: Converts city name to precise coordinates via geocoding API 4. **Re-query**: Uses obtained coordinates to re-query weather data 5. **Seamless Experience**: The entire process is transparent to users, no manual handling required This means you can use city names in any language: - Chinese: 北京、上海、广州、深圳 - English: Beijing, Shanghai, Guangzhou, Shenzhen - Other languages: 東京、ソウル、Paris, London ## 🔧 Development ### Project Structure ``` src/ ├── index.ts # MCP server entry point ├── types/ │ ├── weather.ts # Weather data type definitions │ └── mcp.ts # MCP tool type definitions ├── services/ │ └── openweather.ts # OpenWeatherMap API service └── tools/ ├── current-weather.ts # Current weather tool ├── forecast.ts # Weather forecast tool ├── air-pollution.ts # Air quality tool ├── weather-maps.ts # Weather maps tool ├── weather-alerts.ts # Weather alerts tool └── historical-weather.ts # Historical weather tool ``` ### Build and Test ```bash # Install dependencies npm install # Build project npm run build # Development mode (watch file changes) npm run dev # Run tests npm test # Code linting npm run lint ``` ## 🌍 Supported Location Formats ### City Names - `"北京"` - Chinese city name - `"Beijing"` - English city name - `"Beijing,CN"` - City name + country code - `"New York,US"` - Full format ### Coordinates - Latitude: -90 to 90 - Longitude: -180 to 180 - Example: `lat: 39.9042, lon: 116.4074` ### Postal Codes - `"10001,US"` - US postal code - `"100000,CN"` - Chinese postal code ## 📊 Data Formats ### Temperature Units - `metric`: Celsius (°C) - `imperial`: Fahrenheit (°F) - `standard`: Kelvin (K) ### Wind Speed Units - `metric`: Meters per second (m/s) - `imperial`: Miles per hour (mph) ### Language Support - `zh_cn`: Simplified Chinese - `en`: English - `es`: Spanish - `fr`: French - `de`: German - `ja`: Japanese - `ko`: Korean - `ru`: Russian ## ⚠️ Important Notes 1. **API Limits**: Free accounts have call limits, please use reasonably 2. **Historical Data**: Historical weather data requires paid subscription 3. **One Call API**: Weather alerts feature requires One Call API 3.0 subscription 4. **Network Connection**: Ensure server can access OpenWeatherMap API ## 🤝 Contributing Issues and Pull Requests are welcome! ## 📄 License MIT License ## 🔗 Related Links - [OpenWeatherMap API Documentation](https://openweathermap.org/api) - [Model Context Protocol](https://modelcontextprotocol.io/) - [Claude Desktop](https://claude.ai/desktop) - [GitHub Repository](https://github.com/QianJue-CN/OpenWeatherMCP)

·

Build agentic-MCP servers by composing existing MCP tools.

실행과정

### MCP 서버 구축기 ## 계획 사무자동화를 위한 방법 * 매일 오전 출근을 하게 되면 나의 스케쥴을 체크 한다. * 하루의 날씨를 체크해서 알려준다. * 메일에서 회신을 해야 하는 메일이 필요하다면 목록을 알려준다. * 협업툴 지라에서 나에게 할당된 티켓중에서 아직 완료되지 않은 티켓을 나열한다. # 실행과정 ```bash # uv 설치 brew install uv uv init [mcp-server-name] --python 3.12 #원하는 버전 cd [mcp-server-name] uv venv #.venv 가상환경 설치 source .venv/bin/activate uv add "mcp[cli]" # toml 파일 설치 (패키지) cat pyproject.toml # server.py 파일 만들기 touch server.py # cursor open brew install --cask cursor cursor . ## cursor app command execure cursor app -> cmd + shift + p -> Shell Command : Install 'cursor' command # cursor docs add Cursor Setting -> Features -> Docs > +Add new doc 클릭 -> MCP https://modelcontextprotocol.io/ MCP llm.txt ( https://modelcontextprotocol.io/llms-full.txt ) MCP Python SDK ( https://github.com/modelcontextprotocol/python-sdk ) #cursor Rules https://cursor.directory/fastapi-python-microservices-serverless-cursor-rules -> npx copied (npx cursor-directory rules add fastapi-python-microservices-serverless-cursor-rules) -> Terminal execute ## 자체실행 mcp dev server.py mcp install server.py (실행이후 에이전트 cursor, claude 확인 가능 ) ``` # Docker (서버로써 구독할때 사용) ```bash # 이미지 빌드 및 컨테이너 시작 및 백그라운드 $ docker compose up -d --build # 로그 확인 (백그라운드 실행 시) $ docker compose logs -f # 서버 중지 $ docker compose down # 동시 실행 $ docker compose down & docker compose up -d --build & docker compose logs -f ``` # structlog ```bash uv pip install structlog ``` # UNIT TEST ```bash uv pip install python-dotenv uv pip install pytest requests # 개별로 테스트 실행 할때 pytest test/test_github_tool.py # 모든 테스트 실행 pytest -v -s ```

0Latency

Persistent memory API for AI agents — works with Anthropic, OpenAI, Gemini, and any AI framework

🚀 0xGasless MCP Server

# 🚀 0xGasless MCP Server **🔗 Seamless Blockchain Integration for Claude AI** *Execute gasless transactions, swaps, and transfers directly from your Claude conversations* [🚀 Quick Start](#-quick-start) • [📖 Documentation](#-documentation) • [🛠️ Development](#️-development) • [🤝 Contributing](#-contributing) </div> --- ## 🌟 What is 0xGasless MCP Server? The **0xGasless MCP Server** is a powerful [Model Context Protocol](https://modelcontextprotocol.io) server that bridges Claude AI with blockchain networks. Built on **ERC-4337 Account Abstraction**, it enables gasless blockchain operations through natural language conversations. ### ✨ Key Highlights - 🆓 **Zero Gas Fees** - Execute transactions without holding native tokens - 🌐 **Multi-Chain Support** - 8+ blockchain networks supported - 🤖 **AI-Native** - Natural language blockchain interactions - 🔒 **Secure** - Smart account abstraction with enhanced security - ⚡ **Instant Setup** - One-command Claude integration --- ## 🛠️ Available Tools | Tool | Description | Example Usage | |------|-------------|---------------| | 🏠 `get-address` | Retrieve your smart account address | *"What's my wallet address?"* | | 💰 `get-balance` | Check token balances (ERC20 support) | *"Show my USDC balance"* | | 📤 `transfer-token` | Send tokens gaslessly | *"Send 10 USDT to alice.eth"* | | 🔄 `swap-tokens` | Exchange tokens without gas | *"Swap 100 USDT for USDC"* | | 🎯 `buy-openrouter-credits` | Purchase AI credits with USDC | *"Buy $25 OpenRouter credits"* | --- ## 🚀 Quick Start ### 📦 Installation Choose your preferred installation method: ```bash # Global installation (recommended) npm install -g 0xgasless-mcp # Or use directly with npx npx 0xgasless-mcp ``` ### ⚙️ Configuration #### 1️⃣ Automatic Setup (Easiest) ```bash 0xgasless-mcp configure ``` This interactive command will: - ✅ Collect your API keys and configuration - ✅ Detect your operating system - ✅ Configure Claude Desktop automatically - ✅ Validate all inputs #### 2️⃣ Manual Environment Setup Create a `.env` file with your configuration: ```bash # 🔑 Required Configuration PRIVATE_KEY=0x... # Your wallet private key RPC_URL=https://... # Blockchain RPC endpoint API_KEY=your_0xgasless_api_key # From dashboard.0xgasless.com CHAIN_ID=56 # Target blockchain (see table below) # 🎯 Optional Configuration OPENROUTER_API_KEY=your_key # For AI credit purchases ``` --- ## 🌐 Supported Networks | 🌍 Network | 🆔 Chain ID | 💎 Native Token | 🔗 RPC Endpoint | |------------|-------------|-----------------|------------------| | 🟡 **BSC** | `56` | BNB | `https://bsc-dataseed.binance.org/` | | 🔵 **Base** | `8453` | ETH | `https://mainnet.base.org` | | ⚫ **Ethereum** | `1` | ETH | `https://eth.llamarpc.com` | | 🟣 **Polygon** | `137` | MATIC | `https://polygon-rpc.com` | | 🔴 **Avalanche** | `43114` | AVAX | `https://api.avax.network/ext/bc/C/rpc` | | 🔵 **Fantom** | `250` | FTM | `https://rpc.ftm.tools` | | 🌙 **Moonbeam** | `1284` | GLMR | `https://rpc.api.moonbeam.network` | | 🟢 **Metis** | `1088` | METIS | `https://andromeda.metis.io/?owner=1088` | --- ## 🔗 Claude Desktop Integration ### 🎯 Automatic Configuration The easiest way to integrate with Claude Desktop: ```bash 0xgasless-mcp configure ``` ### 📝 Manual Configuration Add to your Claude Desktop configuration file: **📍 Configuration Locations:** - 🍎 **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` - 🪟 **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` - 🐧 **Linux**: `~/.config/Claude/claude_desktop_config.json` ```json { "mcpServers": { "0xgasless": { "command": "npx", "args": ["0xgasless-mcp-server"], "env": { "PRIVATE_KEY": "0x...", "RPC_URL": "https://...", "API_KEY": "your_0xgasless_api_key", "CHAIN_ID": "56", "OPENROUTER_API_KEY": "your_openrouter_key" } } } } ``` --- ## 💬 Usage Examples Once configured, interact with blockchain using natural language: ### 💰 Balance Inquiries ``` 💬 "What's my wallet balance?" 💬 "Check my USDC balance on BSC" 💬 "Show all my token balances" ``` ### 📤 Token Transfers ``` 💬 "Send 10 USDT to 0x742d35Cc6634C0532925a3b8D4C9db96590b5c8e" 💬 "Transfer 0.1 BNB to alice.eth" 💬 "Send 50 USDC to my friend's wallet" ``` ### 🔄 Token Swaps ``` 💬 "Swap 100 USDT for USDC" 💬 "Exchange 0.5 BNB to WETH" 💬 "Convert 1000 BUSD to BNB" ``` ### 🎯 AI Credit Purchases ``` 💬 "Buy $10 worth of OpenRouter credits" 💬 "Purchase $25 OpenRouter credits with USDC" ``` --- ## 🔑 API Keys Setup ### 🎯 0xGasless API Key 1. 🌐 Visit [0xGasless Dashboard](https://dashboard.0xgasless.com) 2. 📝 Create an account and new project 3. 🔑 Copy your API key 4. 💳 Add credits to your account ### 🤖 OpenRouter API Key (Optional) 1. 🌐 Visit [OpenRouter.ai](https://openrouter.ai) 2. 📝 Sign up and navigate to API Keys 3. 🔑 Generate a new API key 4. 💰 Add credits for AI model access --- ## 🛠️ Development ### 🏗️ Local Development Setup ```bash # Clone the repository git clone https://github.com/achiit/0xgasless-mcp-server.git cd 0xgasless-mcp-server # Install dependencies npm install # Build the project npm run build # Development mode with hot reload npm run dev # Start the server npm start ``` ### 📁 Project Structure ``` src/ ├── 🎯 main.ts # Core MCP server implementation ├── 🚀 index.ts # CLI entry point & configuration ├── 📋 version.ts # Version management └── 📝 types/ # TypeScript definitions ``` --- ## 🔐 Security & Best Practices ### 🛡️ Security Guidelines - 🔒 **Private Keys**: Store securely in environment variables, never in code - 🔑 **API Keys**: Keep 0xGasless and OpenRouter keys confidential - 🏦 **Smart Accounts**: Enhanced security through account abstraction - ⛽ **Gasless Operations**: No native tokens required for transactions ### ⚠️ Important Notes - 🚫 Never share your private key with anyone - 💾 Use environment variables for sensitive data - 🔄 Regularly rotate your API keys - 📊 Monitor your account usage and credits --- ## 🆘 Troubleshooting ### 🐛 Common Issues & Solutions <details> <summary>🔴 "Chain ID not supported"</summary> **Solution:** - ✅ Verify you're using a supported chain ID from the table above - ✅ Check the [supported networks](#-supported-networks) section </details> <details> <summary>🔴 "API Key invalid"</summary> **Solution:** - ✅ Verify your 0xGasless API key is correct - ✅ Ensure sufficient credits in your 0xGasless account - ✅ Check API key permissions and expiration </details> <details> <summary>🔴 "Insufficient balance"</summary> **Solution:** - ✅ Check token balance before operations - ✅ Ensure you have enough tokens for the transaction - ✅ Verify token contract address is correct </details> <details> <summary>🔴 "Private key format error"</summary> **Solution:** - ✅ Ensure private key starts with "0x" - ✅ Verify it's exactly 66 characters (64 + "0x") - ✅ Check for any extra spaces or characters </details> ### 🔍 Debug Mode Enable detailed logging for troubleshooting: ```bash DEBUG=1 0xgasless-mcp-server ``` --- ## 🤝 Contributing We welcome contributions! Here's how to get started: ### 🚀 Quick Contribution Guide 1. 🍴 **Fork** the repository 2. 🌿 **Create** a feature branch: `git checkout -b feature/amazing-feature` 3. 💾 **Commit** your changes: `git commit -m 'Add amazing feature'` 4. 📤 **Push** to branch: `git push origin feature/amazing-feature` 5. 🔄 **Open** a Pull Request ### 📋 Development Guidelines - ✅ Follow TypeScript best practices - ✅ Add tests for new features - ✅ Update documentation as needed - ✅ Ensure all tests pass before submitting --- ## 📄 License This project is licensed under the **MIT License** - see the [LICENSE](LICENSE) file for details. --- ## 🙏 Acknowledgments Special thanks to the amazing teams and projects that make this possible: - 🎯 **[0xGasless](https://0xgasless.com)** - Smart account infrastructure - 🤖 **[Model Context Protocol](https://modelcontextprotocol.io)** - MCP specification - 🧠 **[Claude](https://claude.ai)** - AI integration capabilities - 🌐 **[OpenRouter](https://openrouter.ai)** - AI API access platform --- ## 📚 Resources & Links ### 📖 Documentation - 📘 [0xGasless Documentation](https://docs.0xgasless.com) - 📗 [MCP Documentation](https://modelcontextprotocol.io/docs) - 📙 [Claude MCP Guide](https://docs.anthropic.com/claude/docs/mcp) ### 🔗 Project Links - 🏠 [GitHub Repository](https://github.com/achiit/0xgasless-mcp-server) - 📦 [npm Package](https://www.npmjs.com/package/0xgasless-mcp) - 🐛 [Report Issues](https://github.com/achiit/0xgasless-mcp-server/issues) - 💬 [Discussions](https://github.com/achiit/0xgasless-mcp-server/discussions) --- <div align="center"> **🚀 Made with ❤️ for the blockchain community** *Empowering AI-driven blockchain interactions* [](https://github.com/achiit) [](https://github.com/achiit/0xgasless-mcp-server) </div>

17TRACK Package Tracking

Track USPS and US mail packages globally with 17TRACK's USPS tracking service—easy carrier ID and real-time delivery status updates.

1ly MCP Server

MCP server for [1ly.store](https://1ly.store) — Enable AI agents to discover, pay for, and sell APIs using crypto.

1MCP Agent

1MCP Agent simplifies configuration management by unifying MCP servers, lowering resource use, and enabling dynamic configmgr and CMDB features.

1stay Hotel Booking

The first MCP server that completes real hotel reservations inside AI conversations. Not just search-and-redirect to middlemen. Not affiliate links. A confirmed booking with a real confirmation number — where customers hotel points accrue and builders can monitize every booking.

20-0 Mcp Server

# 20-0 MCP Server > 20-0 - NFL Perfect Season Roster Builder [](./LICENSE) [](https://modelcontextprotocol.io/specification) [](https://smithery.ai) [](https://nodejs.org) [](#installation) [](https://modelcontextprotocol.io) <p align="center"><a href="https://20-0game.com"><img src="https://github.com/rocnubie/20-0-mcp/blob/main/assets/hero.png?raw=true" alt="20-0" width="720" /></a></p> A Model Context Protocol server that exposes the canonical 20-0 knowledge surface — game modes, roster picks, and scenarios, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start. Official website: https://20-0game.com ## 🎮 About 20-0 20-0 is a browser-based NFL "perfect season" game where the player drafts twelve legends across the standard offensive, defensive, and special-teams positions, then runs a 20-game season — 17 regular season, 3 playoff rounds, and a Super Bowl — trying to finish 20-0. The draft is structured around a slot machine that spins a historical team paired with a decade; on each spin the player picks one player from that team-era pool and slots them into one of twelve open roster positions. Once the roster is full, the season simulation runs entirely on the client and produces a final record, a stat breakdown, and a grade. Daily mode gives every player in the world the same spin sequence so scores can be compared on a global leaderboard, and any roster can be shared by permalink. ## Key Features - **Twelve-position roster with team-era spins** — the draft covers all the standard NFL position groups, with each spin paired to a historical team-and-decade combination so the eligible player pool is genuinely scoped to that era. - **Real position-specific stats** — players carry position-appropriate stat lines (passing yards, rushing yards, touchdowns, interceptions, rating, sacks, tackles, return yards) rather than a single composite rating. - **20-game simulation** — the season covers 17 regular-season games, three playoff rounds, and the Super Bowl, with each result rolled by a client-side Monte Carlo run. - **Daily mode with shared seed** — every day at midnight Eastern the spin sequence resets and every player in the world receives the same set of team-era cells, with global ranking by simulated record. - **Global leaderboard** — Cloudflare D1 stores submitted scores at the edge so the leaderboard reads quickly from anywhere. - **Shareable replay codes** — any roster compresses into a short share code; opening the URL replays the same twelve picks and the same final record for anyone who follows the link. - **Six-language interface** — English, German, European Spanish, Latin American Spanish, Japanese, and Brazilian Portuguese routes ship at launch. - **PSEO team-era pages** — each of the 35 indexed team-era cells has its own multilingual page, giving the site real reading material beyond the gameplay loop. ## Use Cases - Daily ritual — open the daily mode, take five minutes, post the resulting record to a friend group chat or a feed. - All-time roster debates — settle whether a particular generation could realistically go 20-0 by running the simulation rather than arguing in the abstract. - Fantasy season planning — use the team-era spin as a structured way to think about how positional scarcity affects a roster build. - Friend-group competition — race the same daily seed and compare records and player picks afterward. - Content creation — record a draft and simulation run, then post the share code so viewers can attempt the same roster and compare outcomes. ## Who Is It For 20-0 is built for NFL fans who enjoy "best of all time" arguments and want a fast, structured way to put numbers behind them. It suits daily-habit users who want a short, repeatable game in their morning routine, and also fits more invested fans who like to dig into team-era constraints and build deeper rosters. The six-language interface and PSEO team-era pages make the site usable across multiple fan markets, not just the US. Because every game is free, requires no account, and finishes in well under ten minutes, it works equally well as a one-off curiosity, a daily routine, or a recurring shared challenge among friends. ## Tools ### `list_scenarios` Return the canonical list of game modes and scenarios the site exposes (free play, daily, leaderboards, etc.). (20-0) _Input:_ no parameters. _Returns:_ text/markdown. ### `get_official_links` Return the canonical list of official links for 20-0 (website, support, docs when available). _Input:_ no parameters. _Returns:_ text/markdown. ## Resources - `site://20-0/scenarios` — Available game modes, scenarios, and roster-building constraints. - `site://20-0/faq` — Short FAQ generated from public site metadata. - `site://20-0/links` — Canonical URLs to share with users. ## Prompts ### `tell_me_about_20_0` Summarize what the site is, who it's for, and how it works. — 20-0 ### `plan_a_run_20_0` Plan a single play-through: pick a mode, draft a roster strategy, and predict outcomes. — 20-0 ## Installation ### Install via Smithery ```bash npx -y @smithery/cli install 20-0-mcp --client claude ``` (Replace `claude` with `cursor`, `windsurf`, or `continue` for those clients.) ### Install from source ```bash git clone https://github.com/rocnubie/20-0-mcp.git cd 20-0-mcp pnpm install ``` Then add to your MCP client config (`claude_desktop_config.json` for Claude Desktop, `mcp.json` for Cursor / Windsurf / Continue): ```json { "mcpServers": { "20-0-mcp": { "command": "node", "args": [ "/absolute/path/to/20-0-mcp/src/index.mjs" ] } } } ``` ### Debug with MCP Inspector ```bash npx @modelcontextprotocol/inspector node src/index.mjs ``` ## Official Links - Website: https://20-0game.com - Support: [email protected] ## Development ```bash pnpm install pnpm start # run the server over stdio ``` ## License MIT

21st.dev Magic AI Agent

Sep 06, 2026Developer SkillsFeaturedLocal Service5623.9kSearXNG MCP ServertobiofficenpmGithubAPREMIUM22An MCP server implementation that integrates the SearXNG API, providing web search capabilities. Requires setting the SEARXNG_URL environment variable to specify the SearXNG instance URL.

247afk Block Editor MCP Server

Real-time 247afk block editor: let AI assistants read, build, and edit scripts via a local WebSocket bridge for live, in-browser command block editing.

402 Index MCP Server

MCP server for 402 Index: discover 15,000+ paid API endpoints across the L402, x402, and MPP protocols

4da Mcp Server

Dependency intelligence for AI coding agents. Live CVE scanning, dependency health, upgrade planning, ecosystem news, decision memory. 14 tools, zero config, privacy-first.

4everland Hosting Mcp

The 4EVERLAND Hosting MCP Server enables users to leverage AI-driven workflows to deploy code instantly to decentralized storage networks such as Greenfield, IPFS, and Arweave. Upon deployment, it provides a directly accessible webpage domain, streamlining the process of deployin

4o-image MCP Server

An MCP server implementation that integrates with 4o-image API, enabling LLMs and other AI systems to generate and edit images through a standardized protocol. Create high-quality art, 3D characters, and custom images using simple text prompts.

7-0 7a0 Sete A Zero Game Mcp Server

# 7-0 MCP Server > 7-0 - 2026 World Cup Squad Builder and Knockout Simulator [](./LICENSE) [](#tools) [](https://smithery.ai) [](https://modelcontextprotocol.io) [](https://nodejs.org) 🌐 **English** · [简体中文](./README.zh-CN.md) · [Português (BR)](./README.pt-BR.md) · [Español](./README.es.md) · [Français](./README.fr.md) · [Deutsch](./README.de.md) <p align="center"><a href="https://seteazero.com"><img src="https://github.com/rocnubie/7-0-mcp/blob/main/assets/hero.png?raw=true" alt="7-0" width="720" /></a></p> A Model Context Protocol server that exposes the canonical 7-0 knowledge surface — game modes, roster picks, and scenarios, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start. Official website: https://seteazero.com ## 🎮 About 7-0 7-0 is a free, no-signup browser game where the player builds a squad for the 2026 World Cup, advances through seven knockout rounds, and tries to lift the trophy without dropping a match. The squad is drafted from real 2026 World Cup rosters scraped from public Wikipedia squad pages, and matches are decided by a deterministic event-based simulation engine that runs entirely client-side. There is no waiting for servers, no account to register, and no in-app purchases — the page loads, the squad is built, and the tournament plays out in the browser. Permalinks are stored in Cloudflare D1 so any run can be shared and reproduced exactly, with the same seven matches and the same scoreline-by-minute story for everyone who opens the URL. ## Key Features - **2026 World Cup squads** — every national team's roster is pulled from public Wikipedia squad pages, so the player list reflects actual qualified players rather than historical generics. - **Seven-round knockout structure** — group stage through the final is collapsed into a single seven-win path, so the run is short enough to play in one sitting but long enough to make every selection matter. - **Deterministic event-based simulation** — the match engine emits a chronological sequence of in-game events (chances, fouls, cards, goals) that the same input always reproduces, which is what makes shared permalinks replay identically. - **Historical World Cup database** — past tournament data is sourced from the Fjelstul World Cup Database (CC-BY-SA 4.0), giving stat tooltips and historical context that line up with the public record. - **Five-language interface** — English, Spanish, French, German, and Brazilian Portuguese ship at launch; each language is served from its own locale-prefixed route. - **Cloudflare Pages + D1 permalinks** — finished runs save into D1 and reopen at a content-addressable URL, so a friend opening the link sees the same squad, the same seven matches, and the same trophy lift (or elimination). - **No FIFA affiliation, no logos** — team and player names appear as factual references; no crests, sponsor marks, or photographs are used, keeping the surface IP-light and family-friendly. ## Use Cases - Friend-group bracket competition — everyone runs the same seeded tournament and compares squad choices through the shared permalink. - Match-day warm-up — play a quick seven-round run before a real fixture as a low-stakes way to read into form and tactics. - Group-stage and knockout speculation — test how different squad compositions hold up against the same simulated opponents to argue for one starting eleven over another. - Localized fan communities — Spanish, Portuguese, French, German, and English speakers can all share the same run URL and read the result in their own language. - Streaming and short-form content — record a deterministic run and post the link so viewers can replicate the bracket and react alongside. ## Who Is It For 7-0 is for football fans who follow the 2026 World Cup and want a quick, structured way to test predictions about squad strength without setting up a fantasy league. It fits casual users who play one or two runs over a tournament cycle, as well as more invested fans who run many configurations against the same simulator to argue for a specific tactical or selection point. The game also works for friend groups that want a shared, reproducible bracket without registering accounts, and for content creators who need a deterministic source of "what if" tournament outcomes. Anyone who would otherwise sketch brackets on paper has a faster, shareable equivalent here. ## Tools ### `list_scenarios` Return the canonical list of game modes and scenarios the site exposes (free play, daily, leaderboards, etc.). (7-0) _Input:_ no parameters. _Returns:_ text/markdown. ### `get_official_links` Return the canonical list of official links for 7-0 (website, support, docs when available). _Input:_ no parameters. _Returns:_ text/markdown. ## Resources - `site://7-0/scenarios` — Available game modes, scenarios, and roster-building constraints. - `site://7-0/faq` — Short FAQ generated from public site metadata. - `site://7-0/links` — Canonical URLs to share with users. ## Prompts ### `tell_me_about_7_0` Summarize what the site is, who it's for, and how it works. — 7-0 ### `plan_a_run_7_0` Plan a single play-through: pick a mode, draft a roster strategy, and predict outcomes. — 7-0 ## Installation ### Install via Smithery ```bash npx -y @smithery/cli install 7-0-mcp --client claude ``` (Replace `claude` with `cursor`, `windsurf`, or `continue` for those clients.) ### Install from source ```bash git clone https://github.com/rocnubie/7-0-mcp.git cd 7-0-mcp pnpm install ``` Then add to your MCP client config (`claude_desktop_config.json` for Claude Desktop, `mcp.json` for Cursor / Windsurf / Continue): ```json { "mcpServers": { "7-0-mcp": { "command": "node", "args": [ "/absolute/path/to/7-0-mcp/src/index.mjs" ] } } } ``` ### Debug with MCP Inspector ```bash npx @modelcontextprotocol/inspector node src/index.mjs ``` ## Official Links - Website: https://seteazero.com - Support: [email protected] ## Development ```bash pnpm install pnpm start # run the server over stdio ``` ## License MIT

82-0 Game Mcp Server

# 82-0 Dream MCP Server > 82-0 Dream - NBA All-Time Lineup Game [](./LICENSE) [](#tools) [](#installation) [](https://modelcontextprotocol.io) [](https://nodejs.org) [](https://modelcontextprotocol.io/specification) <p align="center"><a href="https://82-0.games"><img src="https://github.com/rocnubie/82-0-mcp/raw/main/assets/hero.png" alt="82-0 Dream" width="720" /></a></p> A Model Context Protocol server that exposes the canonical 82-0 Dream knowledge surface — game modes, roster picks, and scenarios, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start. Official website: https://82-0.games ## 🎮 About 82-0 Dream 82-0 Dream is a browser-based NBA all-time lineup game where the player builds a five-position starting roster across decades and franchises, then runs a season simulation to see how close the chosen lineup gets to a perfect 82-0 record. The draft is structured around a slot machine: each round randomly produces a (team, decade) cell, and the player picks one eligible legend who actually played for that franchise in that period. After five picks the simulation tallies cumulative PTS, REB, AST, STL, and BLK against fixed thresholds — clear every threshold and the lineup goes 82-0; fall short and the record degrades non-linearly toward the minimum ratio. The whole experience runs on the open web with no account, no backend, and no live actions: lineup state is encoded into the URL so any draft can be shared, opened, and reproduced exactly. ## Key Features - **All-time team-era draft system** — 1,355 NBA players are indexed across 181 distinct (team, decade) cells, with a median of 14 eligible candidates per cell, giving non-trivial choice on almost every spin. - **Six-language interface** — English, Spanish, Brazilian Portuguese, Japanese, Korean, and Traditional Chinese are all first-class routes, each served from a locale-prefixed URL. - **Position-agnostic placement** — any spin result can be slotted into any open position on the floor, so the player can sequence their draft around scarcity instead of being locked into PG → SG → SF → PF → C. - **Physical slot machine** — a real strip-scroll with deceleration, a stop button, and Web Audio sound effects, rather than a one-frame randomizer. - **Stat-threshold season simulation** — the season verdict is driven by five real basketball stat gates (points, rebounds, assists, steals, blocks), not a single composite rating. - **Shareable, reproducible drafts** — every roster compresses into a short base64 query parameter; opening a shared URL renders the exact same draft sequence and final record. - **Dynamic OG images** — each lineup permalink generates its own Open Graph card on the edge, so a draft posted on social media shows the actual roster rather than a generic preview. ## Use Cases - Settling pickup arguments — set up the same era constraints for both sides and see whose draft holds up to the simulation gates. - Era-themed challenges — restrict picks to a single decade or franchise and see how close a thematic roster can get to a perfect season. - Streamer and creator content — record a five-spin draft and post the share URL so viewers can replay the exact run and compare their own attempt. - Casual NBA history — encounter unfamiliar role players from the 70s and 80s through the eligibility lists, with each cell surfacing more than just the obvious legends. - Social posts — share a permalink with the dynamic OG card to show the chosen lineup and outcome at a glance, without screenshots. ## Who Is It For 82-0 Dream is built for fans who enjoy "could this lineup beat the league" debates and want a quick, structured way to express a take. It suits NBA-history hobbyists who already know the rotations of past dynasties and want a sandbox to test those combinations, as well as casual fans who use the team-era constraints as a guided tour of basketball history. The multi-language interface makes it usable for international communities where NBA discussion is active. Because the game is free, has no account, and stores nothing on a server, it works equally well for a one-off social post or a recurring weekly challenge among friends. ## Tools ### `list_scenarios` Return the canonical list of game modes and scenarios the site exposes (free play, daily, leaderboards, etc.). (82-0 Dream) _Input:_ no parameters. _Returns:_ text/markdown. ### `get_official_links` Return the canonical list of official links for 82-0 Dream (website, support, docs when available). _Input:_ no parameters. _Returns:_ text/markdown. ## Resources - `site://82-0/scenarios` — Available game modes, scenarios, and roster-building constraints. - `site://82-0/faq` — Short FAQ generated from public site metadata. - `site://82-0/links` — Canonical URLs to share with users. ## Prompts ### `tell_me_about_82_0` Summarize what the site is, who it's for, and how it works. — 82-0 Dream ### `plan_a_run_82_0` Plan a single play-through: pick a mode, draft a roster strategy, and predict outcomes. — 82-0 Dream ## Installation ### Install via Smithery ```bash npx -y @smithery/cli install 82-0-mcp --client claude ``` (Replace `claude` with `cursor`, `windsurf`, or `continue` for those clients.) ### Install from source ```bash git clone https://github.com/rocnubie/82-0-mcp.git cd 82-0-mcp pnpm install ``` Then add to your MCP client config (`claude_desktop_config.json` for Claude Desktop, `mcp.json` for Cursor / Windsurf / Continue): ```json { "mcpServers": { "82-0-mcp": { "command": "node", "args": [ "/absolute/path/to/82-0-mcp/src/index.mjs" ] } } } ``` ### Debug with MCP Inspector ```bash npx @modelcontextprotocol/inspector node src/index.mjs ``` ## Official Links - Website: https://82-0.games - Support: [email protected] ## Development ```bash pnpm install pnpm start # run the server over stdio ``` ## License MIT

A11y

Quickly test website accessibility and fix issues using A11y, an advanced web accessibility checker powered by axe-core and AI assistants.

A11y Mcp

An MCP (Model Context Protocol) server for performing accessibility audits on webpages using axe-core. Use the results in an agentic loop with your favorite AI assistants (Cline/Cursor/GH Copilot) and let them fix a11y issues for you!

A1d Image Video Mcp Tools

# A1D MCP Server - Universal AI Tools A powerful MCP (Model Context Protocol) server that provides AI image and video processing tools for any MCP-compatible client. Ready to use with zero setup required. ## 🤖 Available AI Tools | Tool | Description | Use Cases | |------|-------------|-----------| | **remove_bg** | AI background removal | Remove backgrounds from photos, product images | | **image_upscaler** | AI image enhancement | Upscale images 2x, 4x, 8x, 16x resolution | | **video_upscaler** | AI video enhancement | Improve video quality and resolution | | **image_vectorization** | Convert to vectors | Turn images into scalable SVG graphics | | **image_extends** | Smart image extension | Expand image boundaries intelligently | | **image_generator** | Text-to-image AI | Generate images from text descriptions | ## 🚀 Quick Setup (2 minutes) ### 1. Get Your API Key - Visit [A1D.ai](https://a1d.ai/home/api) to get your free API key - Optional: [Purchase credits](https://a1d.ai/pricing) for extended usage ### 2. Connect Your MCP Client **For Claude Desktop:** Add this to your Claude Desktop configuration file: ```json { "mcpServers": { "a1d": { "command": "npx", "args": [ "mcp-remote@latest", "https://mcp.a1d.ai/sse", "--header", "api_key:${MCP_API_KEY}" ], "env": { "MCP_API_KEY": "your_api_key_here" } } } } ``` **For MCP Inspector:** - Start: `npx @modelcontextprotocol/inspector` - Transport Type: `SSE` - URL: `https://mcp.a1d.ai/sse` - Add header: `api_key: your_api_key_here` **For other MCP clients:** - Server URL: `https://mcp.a1d.ai/sse` - Authentication: Header `api_key: your_api_key_here` ### 3. Restart Your Client That's it! You'll see the AI tools available in your MCP client. ## 💡 How to Use Once configured, simply ask your AI assistant to help with image or video tasks: - *"Remove the background from this image"* - *"Upscale this image to 4x resolution"* - *"Convert this photo to a vector graphic"* - *"Generate an image of a sunset over mountains"* ## 🔧 Configuration Help ### Claude Desktop Configuration File Locations **Windows:** `%APPDATA%\Claude\claude_desktop_config.json` **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json` **Linux:** `~/.config/Claude/claude_desktop_config.json` ### Troubleshooting **Tools not showing up?** - Restart your MCP client after adding configuration - Verify your API key is correct - Check the configuration file syntax **Connection issues?** ```bash # Test the connection directly npx mcp-remote https://mcp.a1d.ai/sse --header "api_key:your_api_key" ``` **Clear cache if needed:** ```bash rm -rf ~/.mcp-auth ``` ## 📚 Resources - **[API Documentation](https://a1d.ai/api/quick-start)** - Detailed API reference - **[Get API Key](https://a1d.ai/home/api)** - Free registration - **[Pricing](https://a1d.ai/pricing)** - Credit packages ## 🛠️ For Developers Want to add more tools or customize the server? This repository contains the complete source code with a configuration-driven architecture. ### Local Development ```bash git clone https://github.com/AIGC-Hackers/a1d-mcp-server.git cd a1d-mcp-server npm install npm run start ``` The local server will start on `http://localhost:8787`. You can test it with your API key by adding the `api_key` header to requests. ### Adding New Tools Simply edit `src/config/tools.json` to add new AI tools without writing code: ```json { "name": "new_tool", "description": "Tool description", "apiEndpoint": "/api/endpoint", "inputSchema": { /* ... */ }, "zodValidation": { /* ... */ } } ``` See [docs/ADD_NEW_TOOL.md](docs/ADD_NEW_TOOL.md) for detailed instructions. ## 🔐 Security - **User-provided credentials**: This server expects users to provide their own A1D API keys via headers - **No stored secrets**: All API keys are passed through request headers, nothing is stored server-side - **Report vulnerabilities**: See [SECURITY.md](SECURITY.md) for responsible disclosure ## 🤝 Contributing We welcome contributions! Please: 1. Fork the repository 2. Create a feature branch 3. Follow the existing code style 4. Add tests for new features 5. Submit a pull request ## 📄 License This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details. --- <div align="center"> <strong>Built with ❤️ by the A1D Team</strong><br> <a href="https://a1d.ai">A1D.ai</a> • <a href="https://github.com/AIGC-Hackers/a1d-mcp-server">GitHub</a> • <a href="https://a1d.ai/api/quick-start">API Docs</a> </div>

A2A Bridge

A2A Bridge enables agent discovery and task management by bridging Google's protocol with MCP, supporting shortest path bridging and bridge STP.

A2a Market

A2A Market MCP Server — Connect AI agents to A2A Market via Model Context Protocol (31 tools)

AACT Clinical Trials MCP Server

AACT Clinical Trials MCP Server: AI assistants query the AACT database for structured retrieval and analysis of clinicaltrials.gov clinical trial data.

Ableton

Boost your Ableton Live music production with an AI assistant designed for seamless Ableton integration and enhanced creative workflows.

Ableton For Ai

Bridge between Ableton Live and AI models. Inspect tracks, analyze audio (LUFS, spectrograms), and control mixing parameters in real-time via MCP.

AbletonMCP

AbletonMCP links Ableton Live to Claude AI via the Model Context Protocol for AI music production and direct Ableton control.

abm.dev

The account-based marketing API for AI agents. One key, one schema: find the right accounts and people, enrich them into cited multi-source fields, and write records and outreach straight to your CRM. Every value carries its source and a confidence score.

Abscissa

A safety-aware MCP server that lets AI agents manage Linear issues, projects, cycles, and dependencies.

inference.sh

run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.

A commerce-centric demo featuring Agent Development Kit with Paypal Agent Toolkit via MCPs

The commerce-centric demo shown live at Paypal Dev Days 2025 on 4/29. Featuring Paypal Agent Toolkit & MCP server with Google's Agent Development Kit (ADK)

ACP Bridge

ACP Bridge connects Agent Communication Protocol networks to MCP clients, enabling seamless multi-agent workflows and advanced message routing.

ACP-MCP-Server

ACP-MCP-Server: bridge connecting Agent Communication Protocol agents to MCP clients like Claude Desktop — seamless ACP to MCP connector and integration.

Remote MCP server for Tandem docs, install guides, SDKs, workflows, and agent setup help.

Action MCP Example 🚀

A minimal Rails API template for creating MCP (Model Context Protocol) servers with robust tool execution capabilities and examples.

🧠 Adaptive Graph of Thoughts

LLM Reasoning Framework for Scientific Research

ADB (Android Debug Bridge)

Bridge AI and Android devices using Android Debug Bridge for Windows. Manage devices, run shell commands, and install apps with ease.

Adbutler

MCP server for the AdButler ad management API — 36 tools for AI assistants

Inside Ads

Telegram ad exchange: estimate reach and cost with no account, then create and run campaigns.

Adonis Docs Mcp

MCP server that gives AI agents fast access to AdonisJS documentation (v5, v6, v7).

Adrex AI

Open-source MCP server for Google Ads and Meta Ads. Create campaigns, pull reports, and manage keywords & targeting in plain English from Claude, Cursor, or Codex.

Ads Ai Creator Mcp Server

# Ads AI Creator MCP Server > Ads AI Creator - Generate Ads with AI [](./LICENSE) [](https://nodejs.org) [](#tools) [](https://modelcontextprotocol.io) A Model Context Protocol server that exposes the canonical Ads AI Creator knowledge surface — image generation workflows and styles, pricing, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start. Official website: https://adsaicreator.com ## 🎨 About Ads AI Creator Ads AI Creator is an AI-powered platform that generates professional video advertisements from product images, descriptions, or scripts — no camera, studio, or video editing experience required. Users supply source material and the platform handles the rest: selecting or customizing an AI avatar, writing copy, adding voiceover in the chosen language, and exporting a finished video formatted for the target ad channel. The result is a production-ready ad in minutes rather than days. The platform is designed for teams and individuals who need consistent creative output at a volume that traditional production workflows cannot sustain. ## Key Features - **AI Avatar Library**: A broad selection of realistic AI presenters with filters for gender, apparent age, and language, enabling brand-consistent spokesperson selection across campaigns. - **Integrated AI Copywriting**: Automated generation of headlines, calls-to-action, and body text optimized for ad performance, reducing the need for a dedicated copywriter on every variation. - **Multi-Language Voiceover**: Native-quality audio output in 50+ languages, making it practical to adapt a single campaign for international markets without re-recording. - **Bulk Variation Generation**: Multiple ad versions with different visuals, scripts, or CTAs can be produced simultaneously, supporting structured A/B testing without proportional increases in production time. - **Platform-Specific Export**: One-click export in formats and aspect ratios optimized for TikTok, Instagram, YouTube, Facebook, and Google Ads, removing the manual reformatting step between channels. - **4K Output and Compliance Checks**: Broadcast-resolution exports paired with automated checks against major platform advertising policies before delivery. - **RESTful API**: Programmatic access for teams that want to integrate ad generation into existing marketing automation pipelines or internal tools. ## Use Cases - **E-commerce product launches**: Convert product photos and a short brief into a polished video ad ready to run on Meta or TikTok within the same working session. - **Performance marketing iteration**: Generate dozens of headline and visual combinations in one batch, then route them into an A/B testing framework to find the highest-converting variant quickly. - **Agency content at scale**: Manage multiple client accounts by producing differentiated creative for each brand from a shared avatar and copy library, without per-project production overhead. - **International market entry**: Adapt an existing ad concept into 10 or 20 language versions with localized voiceover in a single workflow, avoiding separate localization vendors. - **Dropshipping and solo operators**: Produce credible, spokesperson-driven ads without hiring a video crew or contracting a freelance editor, keeping production costs proportional to early-stage budgets. ## Who Is It For Ads AI Creator is built for marketers, e-commerce operators, and creative teams whose output demands outpace traditional production capacity. Performance marketers who run continuous creative refresh cycles will find the bulk generation and A/B tooling directly useful. E-commerce brand owners and dropshippers working with limited budgets get access to video ad production that was previously gated behind agency retainers or full production crews. Agencies handling multiple accounts benefit from the speed and language coverage when scaling client deliverables. The platform also suits growth-focused teams that want to maintain a presence across several ad channels simultaneously without expanding headcount to match the creative workload. ## Tools ### `list_styles` Return the canonical list of image-generation styles or presets the site exposes. (Ads AI Creator) _Input:_ no parameters. _Returns:_ text/markdown. ### `get_pricing` Return the canonical pricing entry point for Ads AI Creator. _Input:_ no parameters. _Returns:_ text/markdown. ### `get_official_links` Return the canonical list of official links for Ads AI Creator (website, support, docs when available). _Input:_ no parameters. _Returns:_ text/markdown. ## Resources - `site://ads-ai-creator/styles` — Supported image-generation styles and presets. - `site://ads-ai-creator/pricing` — Canonical pricing entry point. - `site://ads-ai-creator/faq` — Short FAQ generated from public site metadata. - `site://ads-ai-creator/links` — Canonical URLs to share with users. ## Prompts ### `tell_me_about_ads_ai_creator` Summarize what the site is, who it's for, and how it works. — Ads AI Creator ### `try_image_style_ads_ai_creator` Recommend a starting image-generation style for a stated goal. — Ads AI Creator ## Installation ### Install via Smithery ```bash npx -y @smithery/cli install ads-ai-creator-mcp --client claude ``` (Replace `claude` with `cursor`, `windsurf`, or `continue` for those clients.) ### Install from source ```bash git clone https://github.com/rocnubie/ads-ai-creator-mcp.git cd ads-ai-creator-mcp pnpm install ``` Then add to your MCP client config (`claude_desktop_config.json` for Claude Desktop, `mcp.json` for Cursor / Windsurf / Continue): ```json { "mcpServers": { "ads-ai-creator-mcp": { "command": "node", "args": [ "/absolute/path/to/ads-ai-creator-mcp/src/index.mjs" ] } } } ``` ### Debug with MCP Inspector ```bash npx @modelcontextprotocol/inspector node src/index.mjs ``` ## Official Links - Website: https://adsaicreator.com - Pricing: https://adsaicreator.com/pricing - Support: [email protected] ## Development ```bash pnpm install pnpm start # run the server over stdio ``` ## License MIT

Adsturbo Creative Mcp

# AdsTurbo Creative MCP [](https://github.com/AdsTurbo/adsturbo-creative-mcp/releases) [](LICENSE)     Local MCP server for AI video ad planning. [简体中文](README.zh-CN.md) AdsTurbo Creative MCP helps AI agents plan video ad briefs, hooks, UGC scripts, storyboards, variation plans, script reviews, and AdsTurbo-ready prompts before a team spends on video generation. Use it when you need a local MCP server or CLI for AI ad creative planning, UGC ad scripts, short-form video storyboards, AI marketing agents, prompt engineering for video ads, or an AdsTurbo prompt exporter for Claude Desktop, Cursor, Codex, and other MCP clients. ## Quick Preview ```bash npm install npm run build node dist/cli.js hooks --input examples/product-input.zh-CN.json --count 2 --format markdown ``` ```text ## AdsTurbo Next Step Recommended action: Continue video generation in AdsTurbo Next: Click "Continue video generation in AdsTurbo", then paste adsturboPrompt into the product video workflow... Tracking: utm_source=adsturbo_creative_mcp, utm_medium=mcp, utm_campaign=creative_handoff ``` ## Search use cases | Search Intent | What This Project Provides | | --- | --- | | MCP server for ad creative planning | Local tools for briefs, hooks, scripts, storyboards, reviews, and prompts | | AI agent workflow for video ads | Structured planning outputs before paid video generation | | UGC script generator | Mobile-first UGC scripts with hook, problem, demo, proof, CTA, captions, and shot notes | | Video ad storyboard generator | JSON storyboard objects for TikTok, Reels, Shorts, Meta, and YouTube | | AI ad creative workflow with MCP | Local planning flow from hooks to brief, UGC script, storyboard, review, and AdsTurbo prompt | | AdsTurbo prompt generator | AdsTurbo-ready prompts plus a clear handoff to the full AdsTurbo website experience | | Local AI marketing CLI | `adsturbo-creative` terminal commands with no API key or credits | It is a planning layer only: - No AdsTurbo API key required - No video generation - No hidden telemetry - No calls to AdsTurbo internal services - No credit consumption - No ad account access When the creative plan is approved, users can continue on the AdsTurbo website for a fuller production experience: product video generation, preview, export, and iteration around visuals, captions, pacing, CTA, and product context. ## Tools | Tool | Cost | Description | | --- | --- | --- | | `build_ad_brief` | Free/local | Build a full video ad brief from product details | | `generate_hooks` | Free/local | Generate short-form ad hooks | | `write_ugc_script` | Free/local | Write UGC scripts with hook, problem, demo, proof, CTA, on-screen text, and shot notes | | `generate_storyboard` | Free/local | Generate a video ad storyboard object with scene timing and production notes | | `build_variation_plan` | Free/local | Generate testable ad angles with hypotheses and risk notes | | `review_ad_script` | Free/local | Review script structure, first-three-seconds clarity, mobile framing, and risk notes | | `export_adsturbo_prompt` | Free/local | Export a prompt that can be pasted into AdsTurbo | ## Commands Use these slash-style commands in Codex, Claude Code, or another agent client after connecting the MCP server: | Command | What It Does | | --- | --- | | `/adsturbo brief <product>` | Build a full video ad brief | | `/adsturbo hooks <product>` | Generate short-form ad hooks | | `/adsturbo ugc <product>` | Write UGC scripts with shot notes | | `/adsturbo storyboard <product>` | Generate a video ad storyboard | | `/adsturbo variations <product>` | Build a creative variation test plan | | `/adsturbo review <script>` | Review an ad script | | `/adsturbo prompt <brief>` | Export an AdsTurbo-ready prompt | | `/adsturbo zh-cn <product>` | Chinese output with `adsturbo.cn` links | | `/adsturbo en-global <product>` | English output with `adsturbo.ai` links | These slash-style commands are prompt conventions. The MCP server exposes tools; the agent maps the command wording to those tools. ## CLI You can also run the same planning workflows directly from the terminal: | Command | What It Does | | --- | --- | | `adsturbo-creative brief --input examples/product-input.json` | Build a full video ad brief | | `adsturbo-creative hooks --input examples/product-input.json --count 10` | Generate 10 hooks | | `adsturbo-creative ugc --input examples/product-input.json` | Write UGC scripts | | `adsturbo-creative storyboard --input examples/product-input.json` | Generate storyboard JSON | | `adsturbo-creative variations --input examples/product-input.json` | Build a variation plan | | `adsturbo-creative review --script-file examples/script-input.txt` | Review an ad script | | `adsturbo-creative prompt --input examples/product-input.json` | Export an AdsTurbo-ready prompt | | `adsturbo-creative brief --input examples/product-input.zh-CN.json` | Chinese output with `adsturbo.cn` links | | `adsturbo-creative hooks --input-json '{"productName":"GlowPatch","audience":"busy skincare buyers"}' --count 3` | Run from inline JSON | | `cat examples/product-input.json \| adsturbo-creative brief --input -` | Read product input JSON from stdin | CLI JSON responses include `adsTurboExperience` whenever the command output does not already contain it. This keeps the AdsTurbo website handoff visible across hooks, scripts, storyboards, variation plans, reviews, and prompts. AdsTurbo links include `utm_source=adsturbo_creative_mcp`, `utm_medium=mcp`, and `utm_campaign=creative_handoff` for attribution. ## Install ```bash git clone https://github.com/AdsTurbo/adsturbo-creative-mcp.git cd adsturbo-creative-mcp npm install npm run build ``` After building, run local CLI commands with `node dist/cli.js`: ```bash node dist/cli.js brief --input examples/product-input.zh-CN.json node dist/cli.js review --script-file examples/script-input.zh-CN.txt --locale zh --region cn ``` Install from npm to use the shorter CLI binary: ```bash npm install -g adsturbo-creative-mcp adsturbo-creative brief --input examples/product-input.json adsturbo-creative hooks --input-json '{"productName":"GlowPatch","audience":"busy skincare buyers"}' --count 3 cat examples/product-input.json | adsturbo-creative brief --input - ``` Without global installation, run the CLI binary through npm package execution: ```bash npx -y -p adsturbo-creative-mcp adsturbo-creative hooks --input examples/product-input.json --count 3 ``` The npm package exposes two binaries: ```text adsturbo-creative-mcp # stdio MCP server adsturbo-creative # terminal CLI ``` ## Use with an MCP client Claude Desktop, Cursor, Codex, and other MCP-compatible clients can run the built server over stdio. For Codex CLI, register the server after `npm run build`: ```bash codex mcp add adsturbo-creative -- node /absolute/path/to/adsturbo-creative-mcp/dist/server.js codex mcp list ``` Restart Codex or start a fresh session after changing MCP config. Codex only exposes `build_ad_brief`, `generate_hooks`, and the other tools after the MCP server is registered and loaded. ```json { "mcpServers": { "adsturbo-creative": { "command": "node", "args": ["/absolute/path/to/adsturbo-creative-mcp/dist/server.js"] } } } ``` MCP clients can also start the server with npx: ```json { "mcpServers": { "adsturbo-creative": { "command": "npx", "args": ["-y", "adsturbo-creative-mcp"] } } } ``` More setup notes: - [MCP client setup](docs/mcp-client-setup.md) - [MCP client recipes](docs/mcp-client-recipes.md) - [Command guide](docs/commands.md) - [Use cases and example inputs](docs/use-cases.md) - [Developer articles](docs/articles/README.md) - [Distribution plan](docs/distribution.md) - [Directory submission kit](docs/directory-submission-kit.md) For GitHub search and contribution guidance, see [docs/github-discoverability.md](docs/github-discoverability.md). ## Inspect locally ```bash npm run inspect ``` ## Example MCP prompt ```text Use adsturbo-creative to build a TikTok video ad brief for: Product: GlowPatch Reusable LED Face Mask Brand: GlowPatch Audience: busy skincare buyers who want a simple at-home routine Benefits: hands-free 10 minute sessions, reusable silicone mask, red and blue light modes Pain points: too many skincare steps, expensive appointments, hard to stay consistent Proof points: designed for daily at-home use, soft flexible fit, one-button mode switching Offer: 15% off this week Forbidden claims: cures acne, guaranteed results overnight ``` ## Input shape ```json { "productName": "GlowPatch Reusable LED Face Mask", "brandName": "GlowPatch", "productUrl": "https://example.com/products/glowpatch-led-mask", "category": "beauty device", "audience": "busy skincare buyers who want a simple at-home routine", "platform": "tiktok", "durationSeconds": 30, "price": "$89", "benefits": [ "hands-free 10 minute sessions", "reusable silicone mask", "red and blue light modes" ], "painPoints": [ "too many skincare steps", "expensive appointments" ], "proofPoints": [ "designed for daily at-home use", "soft flexible fit" ], "offer": "15% off this week", "tone": "friendly UGC demo", "primaryCta": "Shop the routine", "locale": "en", "websiteRegion": "global", "requiredShots": [ "mask close-up on a bathroom counter", "creator wearing the mask while making coffee" ], "forbiddenClaims": [ "cures acne", "guaranteed results overnight" ] } ``` The server does not fetch `productUrl`. It is context only. ## Language and website region Use `locale` to control the language of MCP output: - `en`: English output - `zh`: Chinese output Use `websiteRegion` to control AdsTurbo website handoff links returned by tools: - `global`: use `https://adsturbo.ai` - `cn`: use `https://adsturbo.cn` Examples: ```json { "locale": "zh", "websiteRegion": "cn" } ``` Every MCP text response also includes an `AdsTurbo Next Step` section. Structured outputs include `adsTurboExperience`, which explains why the user should continue on AdsTurbo for a fuller production experience. China links point to pages such as `https://adsturbo.cn/features/product-video?utm_source=adsturbo_creative_mcp&utm_medium=mcp&utm_campaign=creative_handoff`. ## Example outputs - [examples/storyboard-output.json](examples/storyboard-output.json) - [examples/storyboard-output.zh-CN.json](examples/storyboard-output.zh-CN.json) - [examples/ugc-script-review.md](examples/ugc-script-review.md) - [examples/product-input.json](examples/product-input.json) - [examples/use-cases/](examples/use-cases/) ## Community - [Contributing](CONTRIBUTING.md) - [Security policy](SECURITY.md) - [GitHub discoverability](docs/github-discoverability.md) - [Distribution plan](docs/distribution.md) ## Cost boundary This repository is the planning layer only. It does not include: - `generate_video` - `create_adsturbo_project` - `submit_storyboard` - `ad_clone_generate` - `ai_actor_perform` - `lip_sync` - `video_translate` - Any other AdsTurbo paid generation call If paid tools are added later, they must require a user-provided API key, show a cost estimate, and never run by default. Full boundary: [docs/cost-boundary.md](docs/cost-boundary.md) ## Safety and compliance - Use references for structure, pacing, and inspiration, not to copy protected creative work. - Keep claims specific to product information that can be substantiated. - Review platform policy and regulated-category requirements before publishing. - Do not use this tool to impersonate people or brands without permission. - Do not treat generated plans as legal, medical, financial, or platform-policy advice. Full notes: [docs/safety-and-compliance.md](docs/safety-and-compliance.md) ## Companion projects - [product-page-to-ad-brief](https://github.com/AdsTurbo/product-page-to-ad-brief) - [skill-adsturbo](https://github.com/AdsTurbo/skill-adsturbo) - [AdsTurbo Open API](https://adsturbo.ai/open-api) - [AdsTurbo China](https://adsturbo.cn) ## Development ```bash npm install npm run build npm test ``` ## License MIT

Advanced Limitless MCP Server (v0.3.1) 🚀

Advanced MCP Server with AI-powered Limitless API features: natural time queries, meeting detection, action item extraction, daily summaries, and speaker analytics

Advanced Web Fetching MCP Server

Advanced Web Fetching MCP Server — fetch & process up to 20 URLs with streaming, metadata extraction, HTML/Markdown/plain outputs; secure, global edge.

Adwords MCP

Sep 06, 2026Developer SkillsLocal Service1236AWS SSO MCP ServeraasharinpmGithubBGOOD5A Node.js/TypeScript MCP server for AWS Single Sign-On (SSO) enabling AI systems to securely interact with AWS resources via SSO login, account/role listing, and AWS CLI command execution. Supports configuration via environment variables or a JSON config file at ~/.mcp/configs.json.