Saymaker Mcp

ai.saymakerPublished by saymaker.aiv0.1.1Updated Oct 24, 2026

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

The publisher's own server: Kavel Mcp

VerifiedSTDIODesktop onlyMedia & DesignAI & ML

Overview

AI-generated overview

SayMaker MCP lets an assistant generate and edit AI images and video through SayMaker's hosted models, returning the finished file or a task id.

What you can do
List available image and video models and the inputs each accepts, with credit costs reported per run. Generate images from text with chosen aspect ratio and resolution. Edit an existing photo by describing the change and what must stay. Generate video from text or animate a still image, returning a task id by default. Poll a submitted run's status, or get a link to continue in the SayMaker web app.
When to use it
Useful when you want image or video generation inside a chat client without leaving it, and you already have or are willing to create a SayMaker account with credits. Good for quick text-to-image, targeted photo edits, and short clips from prompts or stills.
Requirements
Runs locally via npx (Node.js) over stdio. Requires a SayMaker API key supplied in the SAYMAKER_API_KEY environment variable, created in the account settings. Network access to SayMaker's service; every run consumes account credits. An optional SAYMAKER_BASE_URL variable overrides the endpoint.
Before you install
Every generation or edit spends credits from your SayMaker account, and video runs can take minutes and queue on free plans. Prompts and any images you pass are sent to SayMaker's hosted service and saved to your account library. The API key is a billable credential, so keep it out of shared configs. Edits and generations write new content to your account.

Installation

In SourceWeft

  1. Open Saymaker Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

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

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

bash
npx saymaker-mcp

Claude Desktop / Claude Code

json
{  "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

bash
gemini extensions install https://github.com/hanshs474/saymaker-mcp

Claude Code plugin

bash
claude plugin marketplace add hanshs474/saymaker-mcpclaude 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.

Source: README.md at commit b2a4092

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v0.1.1LatestOct 5, 2026
  2. v0.1.0Sep 17, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Kavel integrations

Kavel Mcp

ai.kavelOfficial publisher

Kavel MCP lets an assistant find Kavel's AI photo and video effects, build tuned prompts, generate images on a Kavel account, and check credits.

Streamable HTTPWeb executable
Media & Design4 toolsOct 24, 2026

Movoa Mcp

Published by GitHub account hanshs474

Official Movoa MCP server that lets an assistant generate AI video clips with sound from text prompts or photos, using the user's own Movoa credits.

Streamable HTTPWeb executableAuth
Media & Design3 toolsOct 25, 2026

Veida Mcp

ai.veida

A local MCP server that lets an assistant generate AI images from a text prompt through Veida's anonymous free tier, with no API key or account.

STDIODesktop only
Media & DesignNot validated yetOct 24, 2026

Seedance Prompts Mcp

Published by GitHub account hanshs474

A local MCP server that lets an assistant search, read, audit and compose AI video prompts from a bundled set of 150 rendered Seedance prompts.

STDIODesktop only
Knowledge & MemoryNot validated yetOct 27, 2026