Search DevTools

Jump to any tool or page

saymaker-mcp

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

hanshs4740 stars0 forksAI & Agents
View source

Install

Terminal

$npx -y saymaker-mcp

mcp_config.json

{
  "mcpServers": {
    "ai-saymaker-saymaker-mcp": {
      "args": [
        "-y",
        "saymaker-mcp"
      ],
      "command": "npx"
    }
  }
}

Documentation

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

ToolWhat it does
list_modelsEvery image and video model, and the input each one takes
generate_imageText to image, with aspect ratio and resolution
edit_imageChange one thing in a photo and keep the rest
generate_videoText to video, or animate a still you pass in
get_taskPoll a run submitted with wait: false
open_in_saymakerThe 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_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.

Sourced from the repository README.

More in AI & Agents