Saymaker Mcp

ai.saymaker由 saymaker.ai 发布v0.1.1更新于 Oct 24, 2026

Generate and edit AI images and video on SayMaker: Veo 3.1, Kling 3.0, Seedance 2.0, Nano Banana 2.

发布方自己的服务：Kavel Mcp

已验证STDIO仅桌面媒体与设计 AI 与机器学习

服务详情

标识符: ai.saymaker/saymaker-mcp
传输: STDIO
运行时: Desktop only
信任: Verified
发布于: Sep 17, 2026

安全提示

MCP 服务会接收对话中的工具调用请求，并可能执行外部操作。启用前请先了解该服务能做什么，并只授予它所需的权限。

注册中心已验证此服务的命名空间属于 saymaker.ai。它以软件包形式运行，而不是托管端点，因此没有可与该域名比对的端点。

SourceWeft 的检查只涵盖条目是否完整、端点是否响应；不审查服务器的代码，也不审查其工具的行为。

在 README 中添加徽章

向读者展示该 MCP 服务已收录于 SourceWeft，徽章链接到本页。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/ai.saymaker%2Fsaymaker-mcp.svg)](https://sourceweft.com/mcp/ai.saymaker%2Fsaymaker-mcp?utm_source=readme&utm_medium=badge)

概览

AI 生成的概览

SayMaker MCP 让助手通过 SayMaker 的托管模型生成和编辑 AI 图像与视频，返回成品文件或任务 ID。

可以做什么: 列出可用的图像和视频模型及各自接受的输入，并报告每次运行的积分消耗。按文本生成图像，可指定宽高比和分辨率。通过描述修改内容和需保留部分来编辑已有照片。由文本生成视频或将静态图做成动画，默认返回任务 ID。查询已提交任务的进度，或获取在 SayMaker 网页端继续操作的链接。
适用场景: 适合希望在聊天客户端内直接生成图像或视频、不想切换工具的场景，前提是已有或愿意注册带积分的 SayMaker 账户。适用于快速文生图、针对性修图和由提示词或静态图生成短片。
运行要求: 通过 npx（Node.js）以 stdio 在本地运行。需要在 SAYMAKER_API_KEY 环境变量中提供 SayMaker API 密钥，可在账户设置中创建。需要访问 SayMaker 服务的网络连接；每次运行都会消耗账户积分。可选 SAYMAKER_BASE_URL 变量可覆盖服务地址。

安装前请注意

每次生成或编辑都会消耗 SayMaker 账户积分，视频任务可能耗时数分钟，免费方案还需排队。提示词和传入的图片会发送到 SayMaker 托管服务并保存到账户素材库。API 密钥是可计费的凭据，请勿放入共享配置。编辑和生成会向账户写入新内容。

安装

在 SourceWeft 中

打开控制台中的 Saymaker Mcp，将其添加到工作区。
为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照仓库中的启动说明。

README

SayMaker MCP

Run SayMaker's image and video models from any MCP client — Claude, Cursor, Cline, Codex. Ask for a picture or a clip in chat, get the file back.

One credit balance covers the whole shelf: Veo 3.1, Kling 3.0, Seedance 2.0 and 2.5, Nano Banana 2, GPT Image 2.5, Seedream 5.0, Qwen Image 3, MiniMax H3, LTX 2.5, Wan 3.0 and more. Every run reports the exact credit cost it charged, and a run that fails for a technical reason is refunded.

Tools

Tool	What it does
`list_models`	Every image and video model, and the input each one takes
`generate_image`	Text to image, with aspect ratio and resolution
`edit_image`	Change one thing in a photo and keep the rest
`generate_video`	Text to video, or animate a still you pass in
`get_task`	Poll a run submitted with `wait: false`
`open_in_saymaker`	The URL to carry on in the browser

Install

Claude Desktop / Claude Code

json

{  "mcpServers": {    "saymaker": {      "command": "npx",      "args": ["-y", "saymaker-mcp"],      "env": { "SAYMAKER_API_KEY": "sk-..." }    }  }}

{  "mcpServers": {    "saymaker": {      "command": "npx",      "args": ["-y", "saymaker-mcp"],      "env": { "SAYMAKER_API_KEY": "sk-..." }    }  }}

Cursor / Cline

Point the client at npx -y saymaker-mcp (stdio transport) and set SAYMAKER_API_KEY in its environment.

Gemini CLI

Claude Code plugin

API key

Create one at saymaker.ai/settings/apikeys. A key runs on your own account: same models, same credit prices, same plan, and the runs land in your library at saymaker.ai/history.

Every run needs a key; new accounts get sign-up credits. On a free account minimax-h3-fast is the video model that runs, and runs wait in a queue before they start; a plan starts them at once.

Notes

Video takes minutes, so generate_video returns a task id by default. Pass wait: true to block, or poll with get_task.
For an edit, describe the change and what must stay: "change the jacket to dark green, keep the face, pose and background exactly as they are". That second half is what decides whether the edit holds.
SAYMAKER_BASE_URL overrides the endpoint; only useful when testing against a local build of the site.

MIT licensed. Made by SayMaker — the AI video generator agent: say the result, it runs the steps.

来源：README.md，提交 b2a4092