# AdsTurbo (remote · adsturbo.ai)

AI ad creatives: clone reference ads, AI spokesperson videos, video generation, translation, images.

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

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

## Channel facts

- Endpoint: `https://adsturbo.ai/klian/novartapi/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-10-17.

- **Endpoint Security**: 92/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 3063 tokens (~98/item across 31 items; 31 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 41/100
  - 32% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 59% 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 31 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the AdsTurbo MCP server?

AdsTurbo is a hosted endpoint at https://adsturbo.ai/klian/novartapi/mcp, so there is nothing to install locally. 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 --transport http adsturbo-adsturbo 'https://adsturbo.ai/klian/novartapi/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "adsturbo-adsturbo": {
      "url": "https://adsturbo.ai/klian/novartapi/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "adsturbo-adsturbo": {
      "type": "http",
      "url": "https://adsturbo.ai/klian/novartapi/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.adsturbo-adsturbo]
url = "https://adsturbo.ai/klian/novartapi/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "adsturbo-adsturbo": {
      "type": "remote",
      "url": "https://adsturbo.ai/klian/novartapi/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add adsturbo-adsturbo --url 'https://adsturbo.ai/klian/novartapi/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  adsturbo-adsturbo:
    url: "https://adsturbo.ai/klian/novartapi/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "adsturbo-adsturbo": {
      "Transport": "http",
      "Url": "https://adsturbo.ai/klian/novartapi/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add adsturbo-adsturbo -t streamable-http -u 'https://adsturbo.ai/klian/novartapi/mcp'
```

### Other

```json
{
  "mcpServers": {
    "adsturbo-adsturbo": {
      "type": "http",
      "url": "https://adsturbo.ai/klian/novartapi/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-10-16 (score 74, +1)

- [functional] New tool “fetch_video_from_link”

### 2026-10-14 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 13. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 71)

First indexed and scored.

## MCP tools (31)

### `ad_clone_analyze` (~87 tokens)

视频复刻 — 分析

Input parameters:

- `clip_end` (integer): 圈选结束时间（秒）；须 clip_end > clip_start，且 clip_end - clip_start ≤ 12（片段最长 12 秒）
- `clip_start` (integer): 圈选起始时间（秒，非负）
- `video_url` (string): 源视频 URL

### `ad_clone_generate` (~117 tokens)

视频复刻 — 生成

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `duration` (integer): 生成时长（秒）；不在可选值内（含不传）按 12
- `prompt` (string): prompt（可在 Analyze 返回基础上修改）
- `ratio` (string): 视频比例，空 = `9:16`
- `video_url` (string): 源视频片段 URL（Analyze 返回的 video_segment_url）

### `ai_actor_list` (~119 tokens)

系统演员列表

Input parameters:

- `age` (array)
- `ethnicity` (array)
- `gender` (array)
- `industry` (array): 按服务端行业分类过滤（如 `beauty` / `fitness` / `finance` 等）；取值集以服务端注册表为准。
- `limit` (integer)
- `offset` (integer)
- `pose` (array)
- `shot_type` (array)
- `situation` (array)
- `sort_by` (string)

### `ai_actor_perform` (~149 tokens)

演员演出（系统演员或 Persona）

\`actor_id` 既可为系统演员 ID，也可为自定义 Persona 的 `actor_id`，共用同一套演出参数与异步任务响应。

Input parameters:

- `actor_id` (string): 系统演员 ID，或 Persona 的 actor_id
- `auto_emotion` (boolean)
- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `script` (string)
- `similarity` (number)
- `speaker_boost` (boolean)
- `speed` (number)
- `stability` (number)
- `style` (number)

### `ai_actor_say` (~62 tokens)

系统演员语音生成

Input parameters:

- `actor_id` (string)
- `auto_emotion` (boolean)
- `script` (string)
- `similarity` (number)
- `speed` (number)
- `stability` (number)

### `batch_get_work_status` (~27 tokens)

批量查询异步任务状态

Input parameters:

- `workspace_ids` (array)

### `get_persona_status` (~23 tokens)

查询 Persona 状态

Input parameters:

- `actor_id` (string)

### `get_work_status` (~23 tokens)

查询异步任务状态

Input parameters:

- `workspace_id` (string)

### `image_create` (~317 tokens)

图片生成 / 编辑

每次调用固定生成 **1 张**。
默认异步：返回 `workspace_id`（`status=pending`，`result_type=image`），用 `work/status` 轮询取 `result_url`；
\`sync_mod=true` 时同步阻塞到出图，响应里 `result_url` 直接为图片 URL（`status=completed`）。

Input parameters:

- `callback_id` (string): 自定义追踪 ID，在响应中原样回传
- `idempotency_key` (string): 幂等键（预留字段，当前服务端未对本接口做去重）
- `image_urls` (array): 文生图时为空数组；编辑时非空，上限因 model 而异。
- `model` (string): 可选。默认 `nanobanana-pro`。
- `prompt` (string): 生成 / 编辑指令
- `ratio` (string): 取值集因 model 而异，详见请求体表格。
- `resolution` (string): 仅 `nanobanana-pro` / `nano-banana-2` / `nano-banana-2-fast` / `seedream-5.0-pro` / `gpt-image-2` 支持；取值集详见请求体表格。
- `sync_mod` (boolean): `true` 同步阻塞到出图（最长约 60 秒）；默认 `false` 异步返回 `workspace_id`。

### `image_cutout` (~105 tokens)

图片抠图

Input parameters:

- `callback_id` (string): 回调标识
- `idempotency_key` (string): 幂等键，防止重复提交
- `image_url` (string): 原图 URL
- `method` (string): 抠图方法
- `output_format` (string): 输出格式
- `resolution` (string): 输出分辨率
- `workspace_id` (string): 工作空间 ID，用于关联异步任务

### `image_ecommerce` (~131 tokens)

电商产品图

Input parameters:

- `aspect_ratio` (string): 宽高比
- `callback_id` (string): 回调标识
- `idempotency_key` (string): 幂等键
- `language` (string): 语言
- `methods` (array): 生成方法列表
- `product_info` (string): 产品信息
- `reference_image_urls` (array): 参考图片 URL 列表
- `resolution` (string): 输出分辨率
- `user_input` (string): 用户输入描述
- `workspace_id` (string): 工作空间 ID

### `image_enhance` (~94 tokens)

图片增强

Input parameters:

- `callback_id` (string): 回调标识
- `idempotency_key` (string): 幂等键
- `image_url` (string): 原图 URL
- `method` (string): 增强方法
- `resolution` (string): 输出分辨率
- `scale` (integer): 放大倍数
- `workspace_id` (string): 工作空间 ID

### `image_magic_eraser` (~131 tokens)

AI 图片消除

Input parameters:

- `aspect_ratio` (string): 宽高比
- `callback_id` (string): 回调标识
- `idempotency_key` (string): 幂等键
- `image_url` (string): 原图 URL
- `instruction` (string): 消除指令描述
- `mask_url` (string): 蒙版 URL
- `method` (string): 消除方法
- `quantity` (integer): 生成数量
- `resolution` (string): 输出分辨率
- `workspace_id` (string): 工作空间 ID

### `image_poster` (~122 tokens)

活动海报图

Input parameters:

- `aspect_ratio` (string): 宽高比
- `callback_id` (string): 回调标识
- `event_info` (string): 活动信息
- `idempotency_key` (string): 幂等键
- `language` (string): 语言
- `method` (string): 海报生成方法
- `reference_image_urls` (array): 参考图片 URL 列表
- `resolution` (string): 输出分辨率
- `workspace_id` (string): 工作空间 ID

### `persona_create` (~65 tokens)

创建自定义 Persona

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `name` (string)
- `photo_url` (string)
- `voice_audio_url` (string): 可选，用于语音克隆

### `persona_delete` (~21 tokens)

删除自定义 Persona

Input parameters:

- `actor_id` (string)

### `persona_list` (~41 tokens)

个人创建演员列表

分页查询当前用户创建的个人演员（Persona）列表。

Input parameters:

- `limit` (integer)
- `offset` (integer)

### `video_analyze` (~63 tokens)

视频拉片

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `video_url` (string): 源视频 URL
- `workspace_id` (integer): 关联工作区 ID，无则传 0

### `video_character_swap` (~64 tokens)

视频换脸

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `image_url` (string): 目标人脸参考图 URL
- `video_url` (string)
- `workspace_id` (integer)

### `video_edit` (~173 tokens)

视频编辑

\**仅支持 `seedance-2.0` 模型基座**。
源视频二选一：`workspace_id` 或 `video_url`；同时传 / 同时空均报错。
\`mask_url` 可选；非空时为局部编辑掩码。

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `idempotency_key` (string)
- `mask_url` (string)
- `model` (string): 仅支持 `seedance-2.0`。
- `prompt` (string)
- `ratio` (string)
- `reference_images` (array)
- `resolution` (string)
- `video_url` (string)
- `workspace_id` (string)

### `video_enhance_v2` (~95 tokens)

视频增强

Input parameters:

- `callback_id` (string): 回调标识
- `duration` (integer): 时长（秒）
- `idempotency_key` (string): 幂等键
- `method` (string): 增强方法
- `resolution` (string): 输出分辨率
- `video_url` (string): 视频 URL
- `workspace_id` (string): 工作空间 ID

### `video_extend` (~204 tokens)

视频延长（在源视频末尾追加 N 秒）

\**仅支持 `seedance-2.0` 模型基座**。
源视频二选一：`workspace_id`（内部）或 `video_url`（外部）；同时传 / 同时空均报错。
\`duration` 为增量秒数：原 8s + duration=4 → 输出 12s。

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `duration` (integer): 在源视频末尾追加的秒数；范围 4~15，默认 15。
- `idempotency_key` (string)
- `model` (string): 仅支持 `seedance-2.0`。
- `prompt` (string)
- `ratio` (string)
- `resolution` (string)
- `video_url` (string)
- `workspace_id` (string)

### `video_generate` (~283 tokens)

视频生成（文生 / 图生 / 首尾帧 / 多参考媒体）

异步任务；状态走 `/openapi/v1/work/status`，结果走 webhook。
\`model` 各能力差异以服务端注册表为准（duration / ratio / resolution / reference_* 上限按模型而定）。

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `duration` (integer): 视频时长（秒）。取值集 / 范围因 model 而异，详见请求体表格。
- `end_frame` (string): 尾帧图片 URL
- `idempotency_key` (string): 幂等键，相同 key 重复请求复用同一任务
- `model` (string): 模型短名称，省略时走服务端默认。
- `prompt` (string)
- `ratio` (string): 取值集因 model 而异，详见请求体表格。
- `reference_audios` (array)
- `reference_images` (array)
- `reference_videos` (array)
- `resolution` (string): 仅部分模型支持；取值集因 model 而异，详见请求体表格。
- `start_frame` (string): 首帧图片 URL

### `video_inpaint` (~51 tokens)

视频水印消除

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `video_url` (string)
- `workspace_id` (integer)

### `video_lip_sync` (~58 tokens)

视频对口型

Input parameters:

- `audio_url` (string)
- `avatar_url` (string)
- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `prompt` (string)

### `video_magic_eraser` (~84 tokens)

AI 视频消除

Input parameters:

- `callback_id` (string): 回调标识
- `duration` (integer): 时长（秒）
- `idempotency_key` (string): 幂等键
- `method` (string): 消除方法
- `video_url` (string): 视频 URL
- `workspace_id` (string): 工作空间 ID

### `video_motion_control` (~109 tokens)

视频动作控制

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `character_orientation` (string): 角色朝向，默认与视频一致时可传 video
- `image_url` (string)
- `keep_original_sound` (boolean)
- `mode` (string)
- `negative_prompt` (string)
- `prompt` (string)
- `video_url` (string)
- `workspace_id` (integer)

### `video_subtitle` (~80 tokens)

视频字幕

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `source_language` (string)
- `style_type` (string)
- `subtitle_format` (string)
- `translate_language` (string)
- `video_url` (string)
- `workspace_id` (integer)

### `video_translate` (~59 tokens)

视频翻译

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `target_lang` (string): 目标语言
- `video_url` (string)
- `workspace_id` (integer)

### `video_upscale` (~49 tokens)

视频超分

Input parameters:

- `callback_id` (string): 自定义追踪 ID，webhook URL 后台配置
- `video_url` (string)
- `workspace_id` (integer)

### `fetch_video_from_link` (~57 tokens)

解析平台视频链接，换取可用的视频素材

Input parameters:

- `urls` (array, required): 视频分享链接，最多 5 个。可以直接传用户复制来的整段分享文案，会自动取出其中的链接。

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/adsturbo-adsturbo/klian-novartapi-mcp#diagnostics

## Score history

- 2026-10-17: 74
- 2026-10-16: 74
- 2026-10-15: 73
- 2026-10-14: 73
- 2026-10-13: 72
- 2026-10-12: 72
- 2026-10-10: 71

## Common questions

### What is the AdsTurbo MCP server?

AdsTurbo is an MCP server listed in the public MCP registry as io.github.AdsTurbo/adsturbo. AI ad creatives: clone reference ads, AI spokesperson videos, video generation, translation, images. This page covers its hosted endpoint (https://adsturbo.ai/klian/novartapi/mcp).

### Is the AdsTurbo MCP server safe to use?

AdsTurbo scores 74 out of 100 on VerifyMCP. 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 AdsTurbo MCP server expose?

AdsTurbo exposes 31 tools: ad_clone_analyze, ad_clone_generate, ai_actor_list, ai_actor_perform, ai_actor_say, and 26 more. Their descriptions and schemas cost roughly 3,063 tokens of context every time the server is loaded.

### Does the AdsTurbo MCP server require authentication?

Yes. AdsTurbo asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the AdsTurbo MCP server still maintained?

AdsTurbo is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://adsturbo.ai/klian/novartapi/mcp
- Website: https://adsturbo.ai/
- Changelog RSS feed: https://verifymcp.io/servers/adsturbo-adsturbo/klian-novartapi-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/adsturbo-adsturbo/klian-novartapi-mcp.json
- HTML version of this page: https://verifymcp.io/servers/adsturbo-adsturbo/klian-novartapi-mcp