# ai.saymaker/saymaker-mcp (npm · saymaker-mcp)

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

- Trust score: 74/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-25

## Components

- npm · `saymaker-mcp`: 74/100 (this document), [markdown](https://verifymcp.io/servers/ai-saymaker-saymaker-mcp/saymaker-mcp.md), [page](https://verifymcp.io/servers/ai-saymaker-saymaker-mcp/saymaker-mcp)

## Channel facts

- Registry: `npm`
- Package: `saymaker-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-25.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 96 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 8 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 850 tokens (~141/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the ai.saymaker/saymaker-mcp server?

ai.saymaker/saymaker-mcp runs locally as an npm package, launched with npx -y saymaker-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add ai-saymaker-saymaker-mcp -- npx -y saymaker-mcp
```

### Cursor

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

### VS Code

```json
{
  "servers": {
    "ai-saymaker-saymaker-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "saymaker-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ai-saymaker-saymaker-mcp -- npx -y saymaker-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-saymaker-saymaker-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "saymaker-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-saymaker-saymaker-mcp --command npx --arg -y --arg saymaker-mcp
```

### Hermes

```yaml
mcp_servers:
  ai-saymaker-saymaker-mcp:
    command: "npx"
    args: ["-y", "saymaker-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "ai-saymaker-saymaker-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "saymaker-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-saymaker-saymaker-mcp -t stdio -c npx -a -y saymaker-mcp
```

### Other

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-25 (score 74, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-24 (score 73, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-09-17 (score 70)

First indexed and scored.

## MCP tools (6)

### `list_models` (~106 tokens)

List SayMaker models

The image and video models SayMaker runs (Veo 3.1, Kling 3.0, Seedance 2.0, Nano Banana 2, GPT Image 2.5, Seedream 5.0, Qwen Image 3, Wan 3.0 and more), with the input each one takes. Use the returned id with generate_image, edit_image or generate_video.

Input parameters:

- `media` (string): Only image models, or only video models.

### `generate_image` (~184 tokens)

Generate an image

Generate an image from a text prompt on saymaker.ai and return its URL. Runs on your SayMaker credits and reports the exact credit cost. Name subject, framing, light and material in the prompt — vague prompts cost the same as precise ones.

Input parameters:

- `aspect_ratio` (string): e.g. '1:1', '16:9', '9:16', '4:3', '3:4'. Default '1:1'.
- `model` (string): Model id from list_models. Defaults to Nano Banana 2.
- `prompt` (string, required): What the image should show.
- `resolution` (string): Output resolution where the model offers one: '1K', '2K' or '4K'. Bigger costs more credits.
- `wait` (boolean): Wait for the result (default true). False returns a task id to poll.

### `edit_image` (~124 tokens)

Edit an image

Edit a photo you already have: change one thing and keep the rest. Pass the image URL and describe ONLY what should change, plus what must stay ("keep the face and background as they are") — that sentence is what decides whether the edit holds.

Input parameters:

- `image_url` (string, required): Public URL of the image to edit.
- `model` (string): Model id from list_models. Defaults to Nano Banana 2.
- `prompt` (string, required): The change to make, and what must stay unchanged.
- `wait` (boolean): Wait for the result (default true).

### `generate_video` (~306 tokens)

Generate a video

Generate a video clip from a prompt, or animate a still by passing image_url. Runs Veo 3.1, Kling 3.0, Seedance 2.0 and the rest of the SayMaker shelf on your own credits; many of them return sound in the same pass. Needs an API key. On a free account, pass model minimax-h3-fast (480p or 768p, 4 to 15 seconds).

Input parameters:

- `aspect_ratio` (string): e.g. '16:9', '9:16'. Default '16:9'.
- `duration` (number): Clip length in seconds where the model offers a choice, e.g. 4, 6, 8, 10 (MiniMax H3 Fast also 15).
- `image_url` (string): Optional first frame — makes this image-to-video.
- `model` (string): Model id from list_models. Defaults to Seedance 2.0.
- `prompt` (string, required): The shot: what happens, where, how the camera moves.
- `resolution` (string): e.g. '480p', '720p', '1080p', '4k' ('480p' or '768p' on MiniMax H3 Fast).
- `sound` (boolean): Ask for sound where the model writes it in the same pass (default true).
- `wait` (boolean): Wait for the result (default false — video takes minutes).

### `get_task` (~61 tokens)

Check a SayMaker run

Poll a run submitted earlier and return its status and media URL when it is ready.

Input parameters:

- `task_id` (string, required): The task id returned by generate_image, edit_image or generate_video.
- `wait` (boolean): Keep polling until it finishes (default false).

### `open_in_saymaker` (~69 tokens)

Open SayMaker in a browser

The URL to carry on in the browser: the agent that plans multi-step jobs from one sentence, a specific model page, or the image or video maker.

Input parameters:

- `model` (string): Model id, when target is 'model'.
- `target` (string): Defaults to 'agent'.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-saymaker-saymaker-mcp/saymaker-mcp#diagnostics

## Score history

- 2026-09-25: 74
- 2026-09-24: 73
- 2026-09-23: 70
- 2026-09-22: 70
- 2026-09-21: 70
- 2026-09-20: 70
- 2026-09-19: 70
- 2026-09-18: 70
- 2026-09-17: 70

## Common questions

### What is the ai.saymaker/saymaker-mcp server?

ai.saymaker/saymaker-mcp is listed in the public MCP registry as ai.saymaker/saymaker-mcp. Generate and edit AI images and video on SayMaker: Veo 3.1, Kling 3.0, Seedance 2.0, Nano Banana 2. This page covers its npm package (saymaker-mcp).

### Is the ai.saymaker/saymaker-mcp server safe to use?

ai.saymaker/saymaker-mcp scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ai.saymaker/saymaker-mcp server expose?

ai.saymaker/saymaker-mcp exposes 6 tools: list_models, generate_image, edit_image, generate_video, get_task, open_in_saymaker. Their descriptions and schemas cost roughly 850 tokens of context every time the server is loaded.

### Is the ai.saymaker/saymaker-mcp server still maintained?

ai.saymaker/saymaker-mcp is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the ai.saymaker/saymaker-mcp server under?

ai.saymaker/saymaker-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/saymaker-mcp
- Socket report: https://socket.dev/npm/package/saymaker-mcp
- Repository: https://github.com/hanshs474/saymaker-mcp
- Website: https://saymaker.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-saymaker-saymaker-mcp/saymaker-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-saymaker-saymaker-mcp/saymaker-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-saymaker-saymaker-mcp/saymaker-mcp