{"id":29140737,"url":"https://github.com/reinoutww/agentic-mcp-example-ui","last_synced_at":"2026-05-04T22:42:40.475Z","repository":{"id":300564127,"uuid":"1006466721","full_name":"ReinoutWW/agentic-mcp-example-ui","owner":"ReinoutWW","description":"A complete Model Context Protocol (MCP) demonstration featuring a Python FastMCP server with an add() tool, a FastAPI agent backend with OpenAI integration, and a beautiful React frontend with elegant glass morphism design.","archived":false,"fork":false,"pushed_at":"2025-06-22T21:02:07.000Z","size":10897,"stargazers_count":0,"open_issues_count":2,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-05-04T22:42:20.905Z","etag":null,"topics":["agentic-mcp","ai","demo","example","llm","mcp","react"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","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/ReinoutWW.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}},"created_at":"2025-06-22T10:39:59.000Z","updated_at":"2025-06-22T21:02:10.000Z","dependencies_parsed_at":"2025-06-22T18:51:19.413Z","dependency_job_id":null,"html_url":"https://github.com/ReinoutWW/agentic-mcp-example-ui","commit_stats":null,"previous_names":["reinoutww/mcp-proj","reinoutww/agentic-mcp-example-ui"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ReinoutWW/agentic-mcp-example-ui","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ReinoutWW%2Fagentic-mcp-example-ui","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ReinoutWW%2Fagentic-mcp-example-ui/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ReinoutWW%2Fagentic-mcp-example-ui/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ReinoutWW%2Fagentic-mcp-example-ui/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ReinoutWW","download_url":"https://codeload.github.com/ReinoutWW/agentic-mcp-example-ui/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ReinoutWW%2Fagentic-mcp-example-ui/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32628211,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-04T10:08:07.713Z","status":"ssl_error","status_checked_at":"2026-05-04T10:08:02.005Z","response_time":58,"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":["agentic-mcp","ai","demo","example","llm","mcp","react"],"created_at":"2025-06-30T17:40:10.911Z","updated_at":"2026-05-04T22:42:40.461Z","avatar_url":"https://github.com/ReinoutWW.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MCP Demo Project\n\nThis is a complete end-to-end demo showcasing the Model Context Protocol (MCP) with three cleanly separated components:\n\n\n\n![image](https://github.com/user-attachments/assets/c8039c15-2fc0-4703-a9f0-6f1bd923a856)\n\n\n![image](https://github.com/user-attachments/assets/aa53ec6a-63b7-4189-a516-b865df27c311)\n\n\n\n## Architecture\n\n1. **MCP Server** (`mcp-server/`) - Exposes tools over MCP protocol\n2. **Agent Backend** (`agent-backend/`) - OpenAI-Agents loop that uses MCP tools  \n3. **Frontend** (`frontend/`) - React UI for interacting with the agent\n\n## Prerequisites\n\n- Python 3.12+ with virtual environment support\n- Node.js 22+ \n- Docker (optional, for containerized deployment)\n- OpenAI API key\n\n## Quick Start\n\n### 1. Set up Python environment\n\n```bash\npython3 -m venv .venv\nsource .venv/bin/activate\npip install \"mcp[cli]\" openai-agents fastapi uvicorn\n```\n\n### 2. Set up environment variables\n\n```bash\ncp env.example .env\n# Edit .env and add your OpenAI API key\n```\n\n### 3. Run the components\n\n#### Option A: Docker Compose (Recommended)\n\n```bash\ndocker compose up --build\n```\n\nThen open http://localhost:5173\n\n#### Option B: Manual (Development)\n\nTerminal 1 - MCP Server:\n```bash\nsource .venv/bin/activate\ncd mcp-server\npython server.py\n```\n\nTerminal 2 - Agent Backend:  \n```bash\nsource .venv/bin/activate\nexport OPENAI_API_KEY=\"your-key-here\"\ncd agent-backend\npython main.py\n```\n\nTerminal 3 - Frontend:\n```bash\ncd frontend  \nnpm run dev\n```\n\nThen open http://localhost:5173\n\n## Testing\n\n1. Open the frontend in your browser\n2. Type: \"What is 41 + 1?\"\n3. Watch the chain: user → agent → MCP(add) → agent → UI\n\n## Project Structure\n\n```\nmcp-proj/\n├── mcp-server/\n│   ├── server.py          # 40-line MCP server with add() tool\n│   └── Dockerfile\n├── agent-backend/\n│   ├── main.py           # FastAPI app with OpenAI-Agents\n│   └── Dockerfile  \n├── frontend/\n│   ├── src/\n│   │   ├── App.jsx       # Simple chat interface\n│   │   └── main.jsx\n│   ├── package.json\n│   └── Dockerfile\n├── docker-compose.yml\n└── README.md\n```\n\n## Development\n\n### MCP Server Inspector\nTest the MCP server directly:\n```bash\nsource .venv/bin/activate\nmcp dev mcp-server/server.py\n```\n\n### Adding New Tools\nEdit `mcp-server/server.py` and add more `@mcp.tool()` functions:\n\n```python\n@mcp.tool()\ndef multiply(a: int, b: int) -\u003e int:\n    \"\"\"Return a * b\"\"\"\n    return a * b\n```\n\n### Extending the Agent\nThe agent automatically discovers all MCP tools. No changes needed in the backend when adding new tools.\n\n## Ports\n\n- MCP Server: 5000\n- Agent Backend: 8000  \n- Frontend: 5173 (dev) / 4173 (production)\n\n## Troubleshooting\n\n1. **OpenAI API Key**: Make sure `OPENAI_API_KEY` is set in your environment\n2. **Port conflicts**: Check if ports 5000, 8000, or 5173 are already in use\n3. **Docker**: Ensure Docker is running for containerized deployment \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freinoutww%2Fagentic-mcp-example-ui","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freinoutww%2Fagentic-mcp-example-ui","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freinoutww%2Fagentic-mcp-example-ui/lists"}