{"id":40464707,"url":"https://github.com/pulseengine/glsp-mcp","last_synced_at":"2026-01-20T18:04:05.031Z","repository":{"id":301413703,"uuid":"1008566776","full_name":"pulseengine/glsp-mcp","owner":"pulseengine","description":"AI-native graphical modeling platform with WebAssembly component architecture. Features MCP (Model Context Protocol) integration for seamless AI agent interaction,   real-time diagram editing, and WASM-based ADAS (Advanced Driver Assistance Systems) component ecosystem. Built with Rust backend and TypeScript frontend.","archived":false,"fork":false,"pushed_at":"2025-11-13T07:12:21.000Z","size":6248,"stargazers_count":0,"open_issues_count":26,"forks_count":3,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-11-13T07:18:10.299Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pulseengine.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-06-25T18:38:59.000Z","updated_at":"2025-07-30T13:23:06.000Z","dependencies_parsed_at":"2025-07-30T06:13:36.914Z","dependency_job_id":null,"html_url":"https://github.com/pulseengine/glsp-mcp","commit_stats":null,"previous_names":["avrabe/gslp-mcp","pulseengine/glsp-mcp"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/pulseengine/glsp-mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pulseengine%2Fglsp-mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pulseengine%2Fglsp-mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pulseengine%2Fglsp-mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pulseengine%2Fglsp-mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pulseengine","download_url":"https://codeload.github.com/pulseengine/glsp-mcp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pulseengine%2Fglsp-mcp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28607994,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-20T16:10:39.856Z","status":"ssl_error","status_checked_at":"2026-01-20T16:10:39.493Z","response_time":117,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-01-20T18:04:04.917Z","updated_at":"2026-01-20T18:04:05.019Z","avatar_url":"https://github.com/pulseengine.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MCP-GLSP: AI-Native Graphical Modeling Platform\n\n🚀 **The world's first AI-native implementation of the Graphical Language Server Protocol (GLSP)** using the Model Context Protocol (MCP) for universal AI agent compatibility.\n\n## 🌟 Revolutionary Features\n\n- 🤖 **Natural Language → Diagrams**: \"Create a workflow for order processing\" → Complete BPMN diagram\n- 📊 **AI-Powered Analysis**: Intelligent optimization, bottleneck detection, and process improvement\n- 🔧 **Universal AI Access**: Any MCP-compatible AI agent can create and manipulate diagrams\n- 🎨 **Interactive Canvas**: Real-time diagram editing with drag-and-drop\n- ⚡ **Auto-Discovery**: Automatically detects and configures available AI models\n\n## 📊 Current Status\n\n**Functional MVP with Strong Foundation**\n\n✅ **Working Components:**\n- Complete MCP server with 7 diagram tools implemented\n- TypeScript frontend with Canvas rendering\n- Ollama integration with model auto-detection\n- Basic diagram creation and manipulation\n- Comprehensive documentation and startup instructions\n\n⚠️ **Ready for Use:**\n- Creates sample diagrams with basic node types\n- AI generates intelligent diagram planning (text-based)\n- Manual editing supports position updates and basic interactions\n- All three services integrate smoothly\n\n🔧 **Areas for Enhancement:**\n- **AI → Visual**: Currently generates text plans, full visual generation being refined\n- **Canvas Rendering**: Basic shapes working, advanced BPMN/UML symbols in development\n- **Edge Creation**: Tool implemented, UI workflow being polished\n- **File Persistence**: Memory-based storage, file system integration planned\n- **Testing**: Core functionality validated, comprehensive test suite in progress\n\n**Architecture Validation:** This implementation successfully demonstrates that the MCP-GLSP concept works. The foundation is solid and the system is actively usable for diagram creation and AI experimentation.\n\n## 🏗️ Architecture\n\n**Revolutionary Protocol Mapping:**\n- **MCP Resources** → Diagram model state (read-only views)\n- **MCP Tools** → Diagram operations (create, modify, validate)  \n- **MCP Prompts** → AI modeling workflows (guided templates)\n\n**Components:**\n- **Backend**: Rust HTTP server implementing MCP over JSON-RPC\n- **Frontend**: TypeScript web client with Canvas rendering + AI integration\n- **AI Agent**: Ollama LLM integration with intelligent diagram generation\n\n## 🚀 Quick Start\n\n### Prerequisites\n\n1. **Rust** (latest stable)\n   ```bash\n   curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh\n   ```\n\n2. **Node.js** (v18+) and npm\n   ```bash\n   # Download from https://nodejs.org/ or use your package manager\n   node --version  # Should be v18+\n   npm --version\n   ```\n\n3. **Ollama** (for AI features)\n   ```bash\n   # Install from https://ollama.ai/ then:\n   ollama pull llama3.2  # or llama2, mistral, etc.\n   ```\n\n### 🔥 Start the Complete System\n\n**Terminal 1: Start MCP-GLSP Server**\n```bash\ncd glsp-mcp-server\ncargo run --bin server\n```\n*Expected: \"Server listening on http://127.0.0.1:3000\"*\n\n**Terminal 2: Start Frontend + AI Agent**\n```bash\ncd glsp-web-client\nnpm install  # First time only\nnpm run dev\n```\n*Expected: \"Local: http://localhost:5173/\"*\n\n**Terminal 3: Ensure Ollama is Running**\n```bash\n# Check if running:\ncurl http://127.0.0.1:11434/api/tags\n\n# If not running:\nollama serve\n```\n\n### 🎯 Test the AI Workflow\n\n1. **Open**: http://localhost:5173\n2. **Check Status**: AI panel should show 🟢 for both Ollama and MCP connections\n3. **Select Model**: Dropdown automatically populated with your available models\n4. **Enter Description**: \n   ```\n   \"Create a BPMN workflow for customer support ticket resolution with escalation paths\"\n   ```\n5. **Click \"Create Diagram\"**: Watch AI → MCP → Canvas magic! ✨\n\n## 🎨 Usage Examples\n\n### Natural Language Diagram Creation\n```\n\"Create a workflow for e-commerce order fulfillment with payment validation, inventory check, and shipping\"\n```\n→ Complete BPMN diagram with start/end events, tasks, gateways, and proper flow\n\n### AI-Powered Analysis\n- **Analyze Current Diagram**: Get intelligent insights about process efficiency\n- **Optimize Layout**: AI applies best practices for diagram organization\n- **Add Error Handling**: Automatically insert error boundaries and recovery paths\n\n### Manual Editing\n- **Drag \u0026 Drop**: Interactive canvas with real-time editing\n- **Tool Palette**: Create nodes, edges, apply layouts manually\n- **Export**: SVG, JSON, or other formats\n\n## 🔧 Development\n\n### Backend Development\n```bash\ncd glsp-mcp-server\n\n# Run server\ncargo run --bin server\n\n# Run tests\ncargo test\n\n# Build release\ncargo build --release\n```\n\n### Frontend Development\n```bash\ncd glsp-web-client\n\n# Development server\nnpm run dev\n\n# Build for production\nnpm run build\n\n# Type checking\nnpx tsc\n\n# Linting\nnpm run lint\n```\n\n### API Testing\n```bash\n# Test MCP server health\ncurl http://127.0.0.1:3000/health\n\n# Test diagram creation\ncurl -X POST http://127.0.0.1:3000/mcp/rpc \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"jsonrpc\": \"2.0\",\n    \"method\": \"tools/call\",\n    \"params\": {\n      \"name\": \"create_diagram\",\n      \"arguments\": {\"diagramType\": \"workflow\", \"name\": \"Test\"}\n    },\n    \"id\": 1\n  }'\n```\n\n## 📚 Documentation\n\n- **[API Reference](docs/API_REFERENCE.md)**: Complete MCP protocol documentation\n- **[AI Integration Examples](examples/ai_agent_demo.py)**: Python demonstration scripts\n- **[Development Notes](CLAUDE.md)**: Implementation details and architecture decisions\n\n## 🌐 MCP Protocol Integration\n\nThis implementation provides:\n\n### Tools (7 available)\n- `create_diagram`, `create_node`, `create_edge`, `delete_element`\n- `update_element`, `apply_layout`, `export_diagram`\n\n### Resources (Dynamic)\n- `diagram://model/{id}` - Complete diagram state\n- `diagram://validation/{id}` - Validation results  \n- `diagram://metadata/{id}` - Statistics and info\n- `diagram://list` - All available diagrams\n\n### Prompts (6 AI workflows)\n- `generate_workflow`, `optimize_layout`, `add_error_handling`\n- `analyze_diagram`, `create_subprocess`, `convert_diagram`\n\n## 🚀 What Makes This Revolutionary\n\n1. **First AI-Native GLSP**: Traditional GLSP requires manual interaction - this enables pure AI-driven modeling\n2. **Universal AI Compatibility**: Any MCP-compatible AI can connect (Claude Desktop, custom agents, etc.)\n3. **Intelligent Automation**: AI understands diagram semantics, not just visual elements\n4. **Self-Configuring**: Auto-discovers models, handles errors gracefully\n5. **Proven Architecture**: Demonstrates successful MCP-GLSP integration with real working code\n\n## 🤝 Contributing\n\n1. Fork the repository\n2. Create your feature branch (`git checkout -b feature/amazing-feature`)\n3. Commit your changes (`git commit -m 'Add amazing feature'`)\n4. Push to the branch (`git push origin feature/amazing-feature`)\n5. Open a Pull Request\n\n## 📄 License\n\nMIT License - see [LICENSE](LICENSE) file for details.\n\n## 🙏 Acknowledgments\n\n- **Eclipse GLSP**: Original Graphical Language Server Protocol inspiration\n- **Anthropic MCP**: Model Context Protocol specification  \n- **Ollama**: Local LLM runtime\n- **Rust \u0026 TypeScript**: Amazing development ecosystems\n\n---\n\n**🎯 Ready to revolutionize diagram creation with AI?** Start the system and create your first AI-generated diagram in under 2 minutes! 🚀","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpulseengine%2Fglsp-mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpulseengine%2Fglsp-mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpulseengine%2Fglsp-mcp/lists"}