通义万相 MCP 服务器
by Suixinlei
This is a Model Context Protocol (MCP) server based on TypeScript, specifically designed to provide the text-to-image capabilities of Alibaba Cloud's Tongyi Wanxiang. The server allows large language models (LLMs) to directly call Tongyi Wanxiang's image generation API through the MCP protocol.
Last updated: N/A
What is 通义万相 MCP 服务器?
This server is a TypeScript-based Model Context Protocol (MCP) server that integrates with Alibaba Cloud's Tongyi Wanxiang to provide text-to-image generation capabilities to large language models (LLMs). It enables LLMs to generate images by calling Tongyi Wanxiang's API through the MCP protocol.
How to use 通义万相 MCP 服务器?
To use this server, you need to configure your LLM platform (e.g., 百炼) to use the server as an MCP server. This involves specifying the server's command and arguments, and providing the necessary API key for Tongyi Wanxiang. Example configuration for 百炼 platform is provided in the README.
Key features of 通义万相 MCP 服务器
Text-to-Image integration with Tongyi Wanxiang
Asynchronous task processing
MCP protocol support
Configurable polling interval and retry count
Use cases of 通义万相 MCP 服务器
Generating images from text prompts in LLM applications
Integrating AI image generation into conversational AI systems
Creating visual content based on user input
Automated image creation for marketing and advertising
FAQ from 通义万相 MCP 服务器
What is the Model Context Protocol (MCP)?
What is the Model Context Protocol (MCP)?
MCP is a specification that allows LLMs to interact with external tools and services, such as this image generation server.
What is Tongyi Wanxiang?
What is Tongyi Wanxiang?
Tongyi Wanxiang is Alibaba Cloud's AI image generation service.
How do I get a Tongyi Wanxiang API key?
How do I get a Tongyi Wanxiang API key?
You need to have access to Alibaba Cloud's Tongyi Wanxiang service and obtain an API key from the Alibaba Cloud console.
What parameters can I use with the text-to-image API?
What parameters can I use with the text-to-image API?
The API supports parameters such as model, size, n, seed, prompt_extend, and watermark to control the image generation process.
How do I handle asynchronous image generation tasks?
How do I handle asynchronous image generation tasks?
The server provides an API to start image generation tasks and returns a task ID. You can then use another API to retrieve the image generation result using the task ID. The server uses asynchronous polling to check the status of the task.