mcp s
MCP servers built by Truffle AI. Can be used with Dexto to create powerful AI Agents
claude mcp add --transport stdio truffle-ai-mcp-servers npx -y @truffle-ai/gemini-tts-server
How to use
This MCP repository exposes multiple independent servers that can be run with the MCP protocol. The available servers include Music Creator for music generation and audio processing, Image Editor for image manipulation and augmentation, Gemini TTS for text-to-speech generation with Gemini, and Sora Video for AI-driven video creation. Each server is published as a separate npm package and can be launched via the MCP runtime (for example using npx). Once running, you can use the MCP tooling to orchestrate tasks, pipelines, and agents that leverage these capabilities to build AI-powered workflows such as automated music production, image processing pipelines, voice generation with multiple voices and languages, or AI-generated videos from prompts. Refer to the individual server packages for their specific request formats and configuration options.
How to install
Prerequisites:
- Node.js (14.x or newer) and npm installed on your system.
- Optional: a suitable runtime environment (Docker is supported, but this guide covers npm-based setup).
Step-by-step installation:
-
Install Node.js and npm from https://nodejs.org/
-
Install any of the MCP servers from npm (examples shown for each server):
Music Creator:
npm install @truffle-ai/music-creator-serverImage Editor:
npm install @truffle-ai/image-editor-serverGemini TTS:
npm install @truffle-ai/gemini-tts-serverSora Video:
npm install @truffle-ai/sora-video-server -
Run the chosen server via npx (as per mcp_config) or use a runner that supports MCP:
npx -y @truffle-ai/music-creator-serverYou can repeat for image-editor, gemini-tts, and sora-video as needed.
-
If you prefer to install globally or manage via a project, initialize a Node.js project and add the dependencies in package.json, then run your preferred npm script to start the server.
-
Ensure any required API keys or environment variables (such as Gemini TTS credentials) are provided in your environment before starting the servers.
Additional notes
Tips and caveats:
- Each server is published as its own npm package; install only the ones you need for your workflow.
- Gemini TTS may require API keys or credentials; set GEMINI_TTS_API_KEY in your environment if the server demands it.
- Sora Video may require an OpenAI API key or other credentials depending on the generation backend used.
- When running multiple servers, ensure ports do not conflict and that your MCP orchestrator is aware of the server endpoints.
- If using npx to run servers, the -y flag can skip interactive prompts during package resolution.
- Refer to the individual server repositories or README files for detailed configuration options, input formats, and example pipelines.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.