Generate and edit AI images and video on SayMaker: Veo 3.1, Kling 3.0, Seedance 2.0, Nano Banana 2.
Runs on your machine from its package; the steps are below.
At most: creates or changes data: records, files, settings.
Odel charges nothing per call. The publisher may charge for its own service.
Runs locally over stdio
This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).
Run
npx -y saymaker-mcp
MCP client config
{
"mcpServers": {
"saymaker": {
"command": "npx",
"args": [
"-y",
"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.
| 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 |
npx saymaker-mcp
{
"mcpServers": {
"saymaker": {
"command": "npx",
"args": ["-y", "saymaker-mcp"],
"env": { "SAYMAKER_API_KEY": "sk-..." }
}
}
}
Point the client at npx -y saymaker-mcp (stdio transport) and set SAYMAKER_API_KEY in its environment.
gemini extensions install https://github.com/hanshs474/saymaker-mcp
claude plugin marketplace add hanshs474/saymaker-mcp
claude plugin install saymaker@saymaker
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.
generate_video returns a task id by default. Pass wait: true to block, or poll with get_task.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.