About saymaker-mcp
saymaker-mcp connects MCP clients to SayMaker’s image and video generation and editing services. It provides model discovery, task polling, and generated files, with a single SayMaker account credit balance covering the listed models.
Key features
- 01Discover available models and inputs
- 02Generate images from text
- 03Edit images with described changes
- 04Generate video from text or stills
- 05Poll asynchronous video tasks
- 06Continue work in SayMaker browser
Use cases
- 01Create an image from a chat prompt
- 02Animate a supplied still image
- 03Track a video generation task
- 04Revise a photo while preserving specified details
MCP support
The server exposes SayMaker model discovery, image and video generation and editing, task status, and browser handoff tools to MCP clients over stdio.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
6Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| media | enum | No | Only image models, or only video models.image | video |
Details
From the project READMESayMaker 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
npx saymaker-mcp
Claude Desktop / Claude Code
{
"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
gemini extensions install https://github.com/hanshs474/saymaker-mcp
Claude Code plugin
claude plugin marketplace add hanshs474/saymaker-mcp
claude plugin install saymaker@saymaker
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_videoreturns a task id by default. Passwait: trueto block, or poll withget_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_URLoverrides 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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.