
WaveSpeed MCP 服务器——可运行实时目录中的任何模型(图片、视频、音频、3D),并支持模式内省、@path文件上传和报价
概览
WaveSpeed 平台的 MCP 服务器:可运行任何模型——图像、视频、音频、3D —— 来自 Claude Code、Claude Desktop、Cursor、Cline 或任何 MCP 客户端。 基于与开源@wavespeed/cli相同的设计构建: - 目录来自实时API(1小时缓存);新平台模型在发布当天即可运行。- run_model执行任何操作;get_model_schema告诉代理模型实际接受哪些输入,因此模型在写入前先读取。- 唯一显式变换是@path标记——输入内的“@./photo.jpg”值上传文件并替换其托管URL。裸路径未被修改通过。- 在花费前get_price报价,并命名报价盲目输入(unpriced_inputs),而不是将公式的下限作为“该”价格。 如果run_model达到等待限制,任务会继续在服务器端运行——错误标记预测ID,get_prediction接收。
概述(AI 翻译)
WaveSpeed 平台的 MCP 服务器:可运行任何模型,运行 live 目录——图像、视频、音频、3D ——来自 Claude Code、Claude Desktop、Cursor、Cline 或任何 MCP 客户端。
基于与开源@wavespeed/cli相同的设计:
- 无硬编码模型。 目录来自实时 API(1小时缓存);新平台模型在发货当天即可运行。
- 一代动词。
run_model执行任何操作;get_model_schema告诉代理模型实际接受的输入,因此它先读取再写入。 - 输入永远不会变异。 唯一显式变换是
@path标记——input中的"@./photo.jpg"值上传文件并替换其托管的 URL。裸路径通过,未被修改。 - 在花费前报价。
get_price接收与run_model相同的输入并返回估算;实际收取的金额是权威的。
工具
| 工具 | 它的作用 |
|---|---|
list_models |
按文本或模态类型搜索实时目录 |
get_model_schema |
模型的真实输入模式(要求、属性、默认值),并附有指向模型游乐场页面的链接 |
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
WaveSpeed MCP Server
An MCP server for the WaveSpeed platform: run any model on the live catalog — image, video, audio, 3D — from Claude Code, Claude Desktop, Cursor, Cline, or any MCP client.
Built on the same design as the open-source @wavespeed/cli:
- No hardcoded models for
run_model. The catalog comes from the live API (1h cache); new platform models work the day they ship. - One general verb, five shortcuts.
run_modelexecutes anything;get_model_schematells the agent what inputs a model actually accepts, so it reads before it writes.generate_image,edit_image,generate_video,edit_videoandextend_videoskip that: they use the same models as the WaveSpeed /chat page, pick the endpoint for what you give them and fit the request to its live schema. - Inputs are never mutated. The one explicit transform is the
@pathmarker — a"@./photo.jpg"value insideinputuploads the file and substitutes its hosted URL. Bare paths are passed through untouched. The shortcut tools (generate_imageetc.) are the exception: they pick the endpoint and fit the request to the model, and report what they changed innotes. - Quote before you spend.
get_pricetakes the same input asrun_modeland returns an estimate; the amount actually charged for a run is authoritative.
Tools
| Tool | What it does |
|---|---|
list_models |
Search the live catalog by text or modality type |
get_model_schema |
A model’s real input schema (required, properties, defaults), with a link to the model’s playground page |
run_model |
Submit + wait; rejects input keys the model doesn’t accept; @path inputs upload automatically; returns output URLs |
generate_image |
Image from a prompt with the /chat image models (default Seedream 5 Pro); reference images use the model’s edit endpoint |
edit_image |
Edit, restyle or combine existing images with the same models |
安装
npx -y @wavespeed/mcp@latest配置
{
"mcpServers": {
"wavespeed": {
"command": "npx",
"args": ["-y", "@wavespeed/mcp@latest"],
"env": { "WAVESPEED_API_KEY": "wsk_..." }
}
}
}