{"id":24266830,"url":"https://github.com/ejb503/multimodal-mcp-client","last_synced_at":"2025-04-07T09:15:35.237Z","repository":{"id":271553499,"uuid":"913708108","full_name":"Ejb503/multimodal-mcp-client","owner":"Ejb503","description":"A Multi-modal MCP client for voice powered agentic workflows","archived":false,"fork":false,"pushed_at":"2025-02-03T21:39:20.000Z","size":1327,"stargazers_count":152,"open_issues_count":5,"forks_count":21,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-31T08:07:33.658Z","etag":null,"topics":["gemini","mcp","model-context-protocol","voice-assistant"],"latest_commit_sha":null,"homepage":"https://systemprompt.io","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Ejb503.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","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}},"created_at":"2025-01-08T07:50:46.000Z","updated_at":"2025-03-31T03:21:34.000Z","dependencies_parsed_at":null,"dependency_job_id":"b8309fa6-8dca-44af-afe6-c55203871844","html_url":"https://github.com/Ejb503/multimodal-mcp-client","commit_stats":null,"previous_names":["ejb503/multimodal-mcp-client"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ejb503%2Fmultimodal-mcp-client","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ejb503%2Fmultimodal-mcp-client/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ejb503%2Fmultimodal-mcp-client/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ejb503%2Fmultimodal-mcp-client/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ejb503","download_url":"https://codeload.github.com/Ejb503/multimodal-mcp-client/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247622988,"owners_count":20968575,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["gemini","mcp","model-context-protocol","voice-assistant"],"created_at":"2025-01-15T11:28:05.200Z","updated_at":"2025-04-07T09:15:35.214Z","avatar_url":"https://github.com/Ejb503.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Systemprompt Multimodal MCP Client\n\n\u003cdiv align=\"center\"\u003e\n   \n[![Discord](https://img.shields.io/discord/1255160891062620252?color=7289da\u0026label=discord)](https://discord.com/invite/wkAbSuPWpr)\n[![Twitter Follow](https://img.shields.io/twitter/follow/tyingshoelaces_?style=social)](https://twitter.com/tyingshoelaces_)\n[![Linkedin](https://i.sstatic.net/gVE0j.png)](https://www.linkedin.com/in/edjburton/)\n\n[Website](https://systemprompt.io) • [Documentation](https://systemprompt.io/documentation) • [Blog](https://tyingshoelaces.com) • [Get API Key](https://systemprompt.io/console)\n\n\u003c/div\u003e\n\nA modern voice-controlled AI interface powered by Google Gemini and Anthropic MCP (Model Control Protocol). Transform how you interact with AI through natural speech and multimodal inputs.\n\n\u003e **⚠️ Important Note**: This open source project is currently in development and in early access. It is not currently compatible with Safari but has been tested on Chrome with Linux, Windows, and MacOS. If you have any problems, please let us know on Discord or GitHub.\n\nIf you find this project useful, please consider:\n\n- ⭐ Starring it on GitHub\n- 🔄 Sharing it with others\n- 💬 Joining our [Discord community](https://discord.com/invite/wkAbSuPWpr)\n\n## 🌟 Overview\n\nA modern Vite + TypeScript application that enables voice-controlled AI workflows through MCP (Model Control Protocol). This project revolutionizes how you interact with AI systems by combining Google Gemini's multimodal capabilities with MCP's extensible tooling system.\n\nThe Client supports both custom (user provided and configured) and Systemprompt MCP servers. Systemprompt MCP servers can be installed through the UX with a Systemprompt API key (free).\n\nCustom MCP servers are not pre-configured and require a custom configuration file. \n\nCreate a local file `mcp.config.custom.json` in the `config` directory and add your MCP server configuration.\n\n```json\n{\n  \"mcpServers\": {\n    \"my-custom-server\": {\n      \"id\": \"my-custom-server\",\n      \"env\": {\n        \"xxx\": \"xxx\"\n      },\n      \"command\": \"node\",\n      \"args\": [\n        \"/my-custom-server/build/index.js\"\n      ]\n    }\n  }\n}\n```\n\n## 🎯 Why Systemprompt MCP?\n\nTransform your AI interactions with a powerful voice-first interface that combines:\n\n| Feature                             | Description                                                                     |\n| ----------------------------------- | ------------------------------------------------------------------------------- |\n| 🗣️ **Multimodal AI**                | Understand and process text, voice, and visual inputs naturally                 |\n| 🛠️ **MCP (Model Control Protocol)** | Execute complex AI workflows with a robust tooling system                       |\n| 🎙️ **Voice-First Design**           | Control everything through natural speech, making AI interaction more intuitive |\n\n**Perfect for**: Developers building voice-controlled AI applications and looking for innovative ways to use multimodal AI.\n\n## ✨ Core Features\n\n### 🎙️ Voice \u0026 Multimodal Intelligence\n\n- **Natural Voice Control**: Speak naturally to control AI workflows and execute commands\n- **Multimodal Understanding**: Process text, voice, and visual inputs simultaneously\n- **Real-time Voice Synthesis**: Get instant audio responses from your AI interactions\n\n### 🔄 AI Workflow Orchestration\n\n- **Extensible Tool System**: Add custom tools and workflows through MCP\n- **Workflow Automation**: Chain multiple AI operations with voice commands\n- **State Management**: Robust handling of complex, multi-step AI interactions\n\n### 💻 Developer Experience\n\n- **Modern Tech Stack**: Built with Vite, React, TypeScript, and NextUI\n- **Type Safety**: Full TypeScript support with comprehensive type definitions\n- **Hot Module Replacement**: Fast development with instant feedback\n- **Comprehensive Testing**: Built-in testing infrastructure with high coverage\n\n## 🚀 Getting Started\n\n### Prerequisites\n\n- Node.js 16.x or higher\n- npm 7.x or higher\n- A modern browser with Web Speech API support\n\n### Quick Start\n\n1. **Clone the repository**\n\n   ```bash\n   git clone https://github.com/Ejb503/multimodal-mcp-client.git\n   cd multimodal-mcp-client\n   ```\n\n2. **Install dependencies**\n\n   ```bash\n   npm install\n   cd proxy\n   npm install\n   ```\n\n3. **Configure the application**\n\n   ```bash\n   # Navigate to config directory\n   cd config\n\n   # Create local configuration files\n   cp mcp.config.example.json mcp.config.custom.json\n   ```\n\n   Required API Keys:\n\n   - [Google AI Studio](https://ai.google.dev/gemini-api/docs) - Gemini API key\n   - [systemprompt.io/console](https://systemprompt.io/console) - Systemprompt API key\n\n   Add keys to `.env` (see `.env.example` for reference). note that the `VITE_` prefix is required to share the keys with the MCP server and client.\n\n4. **Start development server**\n   ```bash\n   npm run dev\n   ```\n   Access the development server at `http://localhost:5173`\n\n## 🤝 Support \u0026 Community\n\n| Resource   | Link                                                                    |\n| ---------- | ----------------------------------------------------------------------- |\n| 💬 Discord | [Join our community](https://discord.com/invite/wkAbSuPWpr)             |\n| 🐛 Issues  | [GitHub Issues](https://github.com/Ejb503/multimodal-mcp-client/issues) |\n| 📚 Docs    | [Documentation](https://systemprompt.io/documentation)                  |\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 🔮 Future Development\n\nWe're actively working on expanding the capabilities of Systemprompt MCP Client with exciting new features and extensions. Stay tuned for updates!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fejb503%2Fmultimodal-mcp-client","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fejb503%2Fmultimodal-mcp-client","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fejb503%2Fmultimodal-mcp-client/lists"}