{"id":"977aa1bd-6fb5-4f9f-98b1-bc36d48d5b6b","entityType":"agent","slug":"crewai-arun-gupta-mcp-multiplayer-game","name":"mcp-multiplayer-game","canonicalUrl":"https://www.xpersona.co/agent/crewai-arun-gupta-mcp-multiplayer-game","canonicalPath":"/agent/crewai-arun-gupta-mcp-multiplayer-game","generatedAt":"2026-10-09T17:21:23.124Z","source":"GITHUB_REPOS","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"description":"An interactive Tic-Tac-Toe game where three AI agents work together using CrewAI as the agent framework and MCP for distributed communication. 🎮 Agentic Tic-Tac-Toe: Multi-Framework AI with MCP Protocol Support $1 $1 $1 An interactive Tic Tac Toe game where **three AI agents work together** using **CrewAI** as the agent framework and **MCP (Multi-Context Protocol)** for distributed communication. This project showcases how multiple LLMs can collaborate through structured communication protocols - each agent runs as both a CrewAI Agent and an MCP Server. $1","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 5 GitHub stars reported by the source. Last updated 4/15/2026.","installCommand":null,"sourceUrl":"https://github.com/arun-gupta/mcp-multiplayer-game","homepage":null,"primaryLinks":[{"label":"View Source","url":"https://github.com/arun-gupta/mcp-multiplayer-game","kind":"source"}],"safetyScore":66,"overallRank":22,"popularityScore":19,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"An interactive Tic-Tac-Toe game where three AI agents work together using CrewAI as the agent framework and MCP for distributed communication. 🎮 Agentic Tic-Ta"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[{"label":"crewai","status":"self-declared"},{"label":"multi-agent","status":"self-declared"}],"verifiedCount":0,"selfDeclaredCount":3,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"},{"key":"crewai","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"},{"key":"multi-agent","type":"capability","support":"supported","confidenceSource":"profile","notes":"Declared in agent profile metadata"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"}},"adoption":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"medium","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"stars":5,"forks":3,"downloads":null,"packageName":null,"latestVersion":null,"tractionLabel":"5 GitHub stars"},"release":{"evidence":{"source":"agent-index","verified":false,"confidence":"medium","updatedAt":"2026-02-25T05:06:43.485Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T05:21:22.124Z","lastCrawledAt":"2026-02-25T05:06:43.485Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-04T05:06:43.485Z","lastVerifiedAt":null,"highlights":[]},"execution":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":null,"setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-arun-gupta-mcp-multiplayer-game/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-arun-gupta-mcp-multiplayer-game/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-arun-gupta-mcp-multiplayer-game/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/crewai-arun-gupta-mcp-multiplayer-game/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-arun-gupta-mcp-multiplayer-game/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/crewai-arun-gupta-mcp-multiplayer-game/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"GITHUB_REPOS","generatedAt":"2026-10-09T17:21:23.124Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/crewai-arun-gupta-mcp-multiplayer-game/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/crewai-arun-gupta-mcp-multiplayer-game/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/crewai-arun-gupta-mcp-multiplayer-game/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/crewai-arun-gupta-mcp-multiplayer-game/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"GITHUB REPOS","verified":false,"confidence":"high","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":null},"readme":"# 🎮 Agentic Tic-Tac-Toe: Multi-Framework AI with MCP Protocol Support\n\n[![YouTube Demo](https://img.shields.io/badge/YouTube-Demo%20Video-red?style=for-the-badge&logo=youtube)](https://youtu.be/6kMry-zlO3U)\n[![Version](https://img.shields.io/badge/Demo%20Version-v1.0-orange?style=for-the-badge)](https://youtu.be/6kMry-zlO3U)\n[![Latest](https://img.shields.io/badge/Current-v2.0-brightgreen?style=for-the-badge)](#-quick-overview)\n\nAn interactive Tic Tac Toe game where **three AI agents work together** using **CrewAI** as the agent framework and **MCP (Multi-Context Protocol)** for distributed communication. This project showcases how multiple LLMs can collaborate through structured communication protocols - each agent runs as both a CrewAI Agent and an MCP Server.\n\n[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)\n[![FastAPI](https://img.shields.io/badge/FastAPI-0.100+-green.svg)](https://fastapi.tiangolo.com/)\n[![Streamlit](https://img.shields.io/badge/Streamlit-1.28+-red.svg)](https://streamlit.io/)\n[![CrewAI](https://img.shields.io/badge/CrewAI-Agentic%20Framework-orange.svg)](https://github.com/joaomdmoura/crewAI)\n[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)\n\n## 🎯 Quick Overview\n\n- **🎮 Game**: Interactive Tic Tac Toe vs AI team\n- **🤖 AI Team**: Three MCP agents (Scout, Strategist, Executor) - each a CrewAI Agent + MCP Server\n- **🔄 Hot-Swappable Models**: Switch LLMs mid-game without restart via MCP protocol\n- **📊 Real-time Analytics**: MCP protocol monitoring and performance analytics\n- **🎨 Modern UI**: Streamlit dashboard with live updates\n- **🌐 Distributed**: Each agent runs as independent MCP server for scalable deployment\n\n## 🚀 Quick Start\n\n**Get started in 5 minutes!**\n\n### 🎯 **Deployment Modes & Agent Frameworks**\n\nThis project supports multiple deployment modes and agent frameworks:\n\n1. **🚀 Simple Mode (Fastest)** - Direct LLM calls, < 1 second per move, perfect for Tic Tac Toe\n2. **⚡ Optimized Mode (Recommended)** - Shared resources, LangChain direct calls, < 1 second per move\n3. **🏠 Local Mode (Default)** - All agents run in the same Python process with direct method calls\n4. **🌐 Distributed Mode** - Agents run as separate processes communicating via HTTP/JSON-RPC (true MCP transport)\n\n### 📊 **Mode Comparison Table**\n\n| Mode | Framework | Speed | Architecture | Resources | Use Case |\n|------|-----------|-------|-------------|-----------|----------|\n| **🚀 Simple** | Direct LLM | < 1s | Single LLM call | 1 connection | Fastest, simplest |\n| **⚡ Optimized** | LangChain | < 1s | Shared resources | 1 shared connection | Best balance |\n| **🏠 Local** | CrewAI | 3-8s | MCP simulation | 3 LLM connections | Agent coordination |\n| **🌐 Distributed** | CrewAI + MCP | 3-8s | Full MCP protocol | 3 separate processes | Multi-machine |\n\n### 🚀 **Simple Mode Setup (Fastest)**\n\n```bash\n# Simple mode - fastest and most reliable for Tic Tac Toe\ngit clone https://github.com/arun-gupta/mcp-multiplayer-game.git\ncd mcp-multiplayer-game\nchmod +x quickstart.sh\n./quickstart.sh --simple    # or --s for short\n```\n\n**Benefits:**\n- ⚡ **< 1 second per move** - 8-19x faster than complex mode\n- 🔧 **10x simpler** - No CrewAI/MCP overhead\n- 🛠️ **5x easier maintenance** - Direct LLM calls only\n- 🎯 **Perfect for Tic Tac Toe** - No over-engineering\n\n**Access the game**: http://localhost:8501\n**API Documentation**: http://localhost:8000/docs\n\n### ⚡ **Optimized Mode Setup (Recommended)**\n\n```bash\n# Optimized mode - best balance of speed and structure\ngit clone https://github.com/arun-gupta/mcp-multiplayer-game.git\ncd mcp-multiplayer-game\nchmod +x quickstart.sh\n./quickstart.sh --optimized    # or --o for short\n```\n\n**Benefits:**\n- ⚡ **< 1 second per move** - Shared resources, no MCP servers\n- 🔧 **LangChain direct calls** - No CrewAI overhead\n- 🛠️ **Shared Ollama connection** - Memory efficient\n- 🎯 **Pre-created tasks** - No runtime creation overhead\n- 🚀 **Best balance** - Speed + structure\n\n**Access the game**: http://localhost:8501\n**API Documentation**: http://localhost:8000/docs\n\n### 🏠 **Local Mode Setup (Default)**\n\n```bash\n# Clone and setup MCP hybrid architecture automatically\ngit clone https://github.com/arun-gupta/mcp-multiplayer-game.git\ncd mcp-multiplayer-game\nchmod +x quickstart.sh\n./quickstart.sh\n```\n\n**Access the game**: http://localhost:8501\n**API Documentation**: http://localhost:8000/docs\n\n### 🤖 **Agent Framework Options**\n\nChoose between different agent frameworks:\n\n```bash\n# Simple mode (fastest, recommended for Tic Tac Toe)\n./quickstart.sh --simple    # or --s for short\n\n# Optimized mode (best balance, recommended)\n./quickstart.sh --optimized    # or --o for short\n\n# LangChain agents (faster than CrewAI)\n./quickstart.sh --langchain\n\n# CrewAI agents with MCP protocol (complex, full coordination)\n./quickstart.sh --crewai\n```\n\n**Framework Comparison:**\n- **Simple**: Direct LLM calls, < 1 second per move, perfect for Tic Tac Toe\n- **Optimized**: LangChain with shared resources, < 1 second per move, best balance\n- **LangChain**: Direct LLM calls, faster than CrewAI, good balance\n- **CrewAI**: Full agent coordination with MCP protocol, most complex\n\n### 🌐 **Distributed Mode Setup**\n\nFor true MCP protocol transport between agents:\n\n```bash\n# Clone and setup\ngit clone https://github.com/arun-gupta/mcp-multiplayer-game.git\ncd mcp-multiplayer-game\nchmod +x quickstart.sh\n./quickstart.sh -d  # or --d, --dist, --distributed all work\n```\n\nThis starts:\n- **Scout Agent** on port 3001\n- **Strategist Agent** on port 3002\n- **Executor Agent** on port 3003\n- **Main API Server** on port 8000 (with `--distributed` flag)\n\n**Access the game**: http://localhost:8501\n**API Documentation**: http://localhost:8000/docs\n\n### 🔧 **Manual Setup (Alternative)**\n\n```bash\n# Clone and setup MCP hybrid architecture\ngit clone https://github.com/arun-gupta/mcp-multiplayer-game.git\ncd mcp-multiplayer-game\n\n# Install dependencies\npython -m venv venv\nsource venv/bin/activate  # Windows: venv\\Scripts\\activate\npip install -r requirements.txt\n\n# Install Ollama models (optional)\nollama pull llama2:7b\nollama pull mistral\n\n# Optimize Ollama for instant AI responses (recommended)\nOLLAMA_KEEP_ALIVE=-1 ollama run llama3.2:1b\n\n# Start MCP API server\npython main.py &\n\n# Start Streamlit UI (in another terminal)\npython run_streamlit.py\n```\n\n### 🎮 **What the Quickstart Script Does**\n\nThe `quickstart.sh` script automatically:\n- ✅ **Process cleanup** - Kills existing processes on ports 8000/8501\n- ✅ **Environment setup** - Creates venv and installs dependencies\n- ✅ **Python version checking** - Validates Python 3.11+\n- ✅ **Dependency installation** - Installs all requirements with Python 3.13 compatibility\n- ✅ **Ollama model setup** - Optional local model installation\n- ✅ **File validation** - Checks for all required files\n- ✅ **Application startup** - Starts both backend and frontend services\n- ✅ **Error handling** - Comprehensive error checking and colored output\n\n### 🚀 **Advanced Usage**\n\n```bash\n# Full setup and launch (default)\n./quickstart.sh\n\n# Launch only (skip setup, venv must exist)\n./quickstart.sh --skip-setup\n\n# Setup and launch without cleanup\n./quickstart.sh --skip-cleanup\n\n# Show help\n./quickstart.sh --help\n```\n\n📖 **[Complete Setup Guide](docs/QUICKSTART.md)** - Detailed instructions and troubleshooting\n\n## 📚 Documentation\n\n### **📖 Guides & Tutorials**\n- **[📋 Quick Start Guide](docs/QUICKSTART.md)** - Complete setup and troubleshooting\n- **[🎨 Streamlit UI Guide](docs/README_STREAMLIT.md)** - Frontend features and customization\n\n### **📚 Reference Documentation**\n- **[🏗️ Architecture](docs/ARCHITECTURE.md)** - System architecture and design\n- **[📡 API Reference](docs/API.md)** - Complete API documentation and examples\n- **[🎮 User Guide](docs/USER_GUIDE.md)** - Game experience and setup instructions\n- **[🚀 Features](docs/FEATURES.md)** - Detailed feature explanations and capabilities\n- **[🛠️ Development](docs/DEVELOPMENT.md)** - Development workflow and contribution guidelines\n\n### **🔗 MCP Protocol Documentation**\n- **[🔍 MCP Query Guide](docs/MCP_QUERY_GUIDE.md)** - All methods to query MCP servers (Recommended starting point)\n- **[🌐 REST API Guide](docs/MCP_REST_API_GUIDE.md)** - Detailed REST/HTTP API reference with Python examples\n- **[📋 MCP Protocol](docs/MCP_PROTOCOL.md)** - Complete MCP protocol implementation details\n\n## 🔑 API Keys Setup\n\nTo use the AI agents, you'll need API keys for the LLM providers. See the **[User Guide](docs/USER_GUIDE.md)** for detailed setup instructions.\n\n## ⚙️ Configuration\n\nThe application uses `config.json` for all configuration settings. Copy the example file and customize as needed:\n\n```bash\ncp config.example.json config.json\n```\n\n### Configuration Options:\n\n```json\n{\n  \"mcp\": {\n    \"ports\": {\n      \"scout\": 3001,       // MCP server port for Scout agent\n      \"strategist\": 3002,  // MCP server port for Strategist agent\n      \"executor\": 3003     // MCP server port for Executor agent\n    },\n    \"host\": \"localhost\",\n    \"protocol\": \"http\"\n  },\n  \"api\": {\n    \"host\": \"0.0.0.0\",\n    \"port\": 8000           // FastAPI server port\n  },\n  \"streamlit\": {\n    \"host\": \"0.0.0.0\",\n    \"port\": 8501           // Streamlit UI port\n  },\n  \"models\": {\n    \"default\": \"gpt-5-mini\",  // Default model for all agents\n    \"fallback\": [\"gpt-4\", \"claude-3-sonnet\", \"llama3.2:3b\"]\n  },\n  \"performance\": {\n    \"mcp_coordination_timeout\": 15,     // Timeout for MCP coordination (seconds)\n    \"agent_execution_timeout\": 8,       // Timeout for individual agent tasks (seconds)\n    \"enable_metrics\": true              // Enable/disable performance metrics\n  }\n}\n```\n\n**Note:** `config.json` is gitignored for security. Always use `config.example.json` as a template.\n\n---\n\n## 🏗️ Architecture\n\nThe system uses **MCP (Multi-Context Protocol)** for distributed communication between CrewAI agents. Each agent runs as both a CrewAI Agent and an MCP Server, enabling modular, scalable deployment.\n\n### **Key Components**\n- **🤖 MCP Agents**: Scout, Strategist, Executor (Ports 3001-3003)\n- **🌐 FastAPI Server**: Main application server (Port 8000)\n- **🎨 Streamlit UI**: Interactive game interface (Port 8501)\n- **📡 MCP Coordinator**: Orchestrates agent communication with streamlined real-time coordination\n\n### **🚀 Streamlined MCP Coordination**\n\nFor optimal real-time gaming performance, the system uses a **lightweight MCP coordination approach**:\n\n- **⚡ Fast Response Times**: Sub-second AI moves via optimized agent communication\n- **🎯 Strategic Logic**: Direct blocking/winning move detection for immediate threats\n- **📊 Real-Time Metrics**: Accurate request tracking with microsecond precision\n- **🔄 Auto-AI Moves**: Automatic AI turn triggering via dedicated `/ai-move` endpoint\n- **🎮 Seamless UX**: No delays or timeouts during gameplay\n\n### **API Endpoints**\n\n#### 🌐 **FastAPI Server Endpoints** (Port 8000)\n*Main application server that coordinates everything*\n\n| Endpoint | Method | Description |\n|----------|--------|-------------|\n| `/` | GET | Root endpoint |\n| `/state` | GET | Get current game state |\n| `/make-move` | POST | Make a player move and get AI response |\n| `/ai-move` | POST | Trigger AI move (auto-called when AI's turn) |\n| `/reset-game` | POST | Reset game |\n| `/agents/status` | GET | Get all agent status |\n| `/agents/{agent_id}/switch-model` | POST | Switch agent model |\n| `/mcp-logs` | GET | Get MCP protocol logs |\n| `/agents/{agent_id}/metrics` | GET | Get agent performance metrics (real-time) |\n| `/health` | GET | Health check |\n\n#### 🤖 **MCP Agent Server Tools** (Ports 3001-3003)\n*Individual agent MCP servers exposing tools for direct communication*\n\n> **📝 MCP Tools**: These are **tools** (actions/operations) that agents can perform, representing capabilities like \"analyze\", \"create\", \"execute\".\n\n### **🔍 Scout Agent MCP Server** (Port 3001)\nThe Scout agent analyzes the game board and identifies patterns, threats, and opportunities.\n\n| Tool | Description | Parameters |\n|------|-------------|------------|\n| `analyze_board` | Analyze board state and provide comprehensive insights | `board`, `current_player`, `move_number` |\n| `detect_threats` | Identify immediate threats from opponent | `board_state` |\n| `identify_opportunities` | Find winning opportunities and strategic positions | `board_state` |\n| `get_pattern_analysis` | Analyze game patterns and trends | `board_state`, `move_history` |\n\n### **🧠 Strategist Agent MCP Server** (Port 3002)\nThe Strategist agent creates game plans and recommends optimal moves.\n\n| Tool | Description | Parameters |\n|------|-------------|------------|\n| `create_strategy` | Generate strategic plan based on Scout's analysis | `observation_data` |\n| `evaluate_position` | Evaluate current position strength | `board_state`, `player` |\n| `recommend_move` | Recommend best move with detailed reasoning | `board_state`, `available_moves` |\n| `assess_win_probability` | Calculate win probability for current state | `board_state`, `player` |\n\n### **⚡ Executor Agent MCP Server** (Port 3003)\nThe Executor agent validates and executes moves on the game board.\n\n| Tool | Description | Parameters |\n|------|-------------|------------|\n| `execute_move` | Execute strategic move on the board | `move_data`, `board_state` |\n| `validate_move` | Validate move legality and game rules | `move`, `board_state` |\n| `update_game_state` | Update game state after move execution | `move`, `current_state` |\n| `confirm_execution` | Confirm move execution and return results | `execution_result` |\n\n### **🔄 Common Agent Tools** (All Ports)\nAll agents share these standard MCP capabilities:\n\n| Tool | Description | Purpose |\n|------|-------------|---------|\n| `execute_task` | Execute CrewAI task via MCP protocol | Task execution |\n| `get_status` | Get agent status and current state | Health monitoring |\n| `get_memory` | Retrieve agent memory and context | State management |\n| `switch_model` | Hot-swap LLM model without restart | Model switching |\n| `get_metrics` | Get real-time performance metrics | Performance tracking |\n\n**📚 [Complete Architecture & API Documentation](docs/ARCHITECTURE.md)** - Detailed architecture diagrams, communication flows, and complete API reference.\n\n---\n\n## 📊 Monitoring & Analytics\n\nThe Streamlit dashboard provides comprehensive monitoring with real-time analytics, performance tracking, and MCP protocol logging.\n\n**📚 [Features Documentation](docs/FEATURES.md)** - Detailed monitoring capabilities, analytics, and feature status.\n\n---\n\n## 📄 License\n\nThis project is licensed under the **Apache License, Version 2.0** - see the [LICENSE](LICENSE) file for details. ","readmeExcerpt":"🎮 Agentic Tic-Tac-Toe: Multi-Framework AI with MCP Protocol Support $1 $1 $1 An interactive Tic Tac Toe game where **three AI agents work together** using **CrewAI** as the agent framework and **MCP (Multi-Context Protocol)** for distributed communication. This project showcases how multiple LLMs can collaborate through structured communication protocols - each agent runs as both a CrewAI Agent and an MCP Server. $1","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"# Simple mode - fastest and most reliable for Tic Tac Toe\ngit clone https://github.com/arun-gupta/mcp-multiplayer-game.git\ncd mcp-multiplayer-game\nchmod +x quickstart.sh\n./quickstart.sh --simple    # or --s for short"},{"language":"bash","snippet":"# Optimized mode - best balance of speed and structure\ngit clone https://github.com/arun-gupta/mcp-multiplayer-game.git\ncd mcp-multiplayer-game\nchmod +x quickstart.sh\n./quickstart.sh --optimized    # or --o for short"},{"language":"bash","snippet":"# Clone and setup MCP hybrid architecture automatically\ngit clone https://github.com/arun-gupta/mcp-multiplayer-game.git\ncd mcp-multiplayer-game\nchmod +x quickstart.sh\n./quickstart.sh"},{"language":"bash","snippet":"# Simple mode (fastest, recommended for Tic Tac Toe)\n./quickstart.sh --simple    # or --s for short\n\n# Optimized mode (best balance, recommended)\n./quickstart.sh --optimized    # or --o for short\n\n# LangChain agents (faster than CrewAI)\n./quickstart.sh --langchain\n\n# CrewAI agents with MCP protocol (complex, full coordination)\n./quickstart.sh --crewai"},{"language":"bash","snippet":"# Clone and setup\ngit clone https://github.com/arun-gupta/mcp-multiplayer-game.git\ncd mcp-multiplayer-game\nchmod +x quickstart.sh\n./quickstart.sh -d  # or --d, --dist, --distributed all work"},{"language":"bash","snippet":"# Clone and setup MCP hybrid architecture\ngit clone https://github.com/arun-gupta/mcp-multiplayer-game.git\ncd mcp-multiplayer-game\n\n# Install dependencies\npython -m venv venv\nsource venv/bin/activate  # Windows: venv\\Scripts\\activate\npip install -r requirements.txt\n\n# Install Ollama models (optional)\nollama pull llama2:7b\nollama pull mistral\n\n# Optimize Ollama for instant AI responses (recommended)\nOLLAMA_KEEP_ALIVE=-1 ollama run llama3.2:1b\n\n# Start MCP API server\npython main.py &\n\n# Start Streamlit UI (in another terminal)\npython run_streamlit.py"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[],"languages":["python"],"docsSourceLabel":"GITHUB REPOS","editorialOverview":"An interactive Tic-Tac-Toe game where three AI agents work together using CrewAI as the agent framework and MCP for distributed communication. 🎮 Agentic Tic-Tac-Toe: Multi-Framework AI with MCP Protocol Support $1 $1 $1 An interactive Tic Tac Toe game where **three AI agents work together** using **CrewAI** as the agent framework and **MCP (Multi-Context Protocol)** for distributed communication. This project showcases how multiple LLMs can collaborate through structured communication protocols - each agent runs as both a CrewAI Agent and an MCP Server. $1","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":397,"uniquenessScore":61,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T05:21:22.124Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:21:23.124Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/github_repos","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}