AdsTurbo
Server Details
AI ad creatives: clone reference ads, AI spokesperson videos, video generation, translation, images.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- AdsTurbo
- Claude
- –
TDQS
Scored across 32 tools
Most tools are cleanly separated by resource prefix (image_*, video_*, persona_*, ai_actor_*), but several pairs have fuzzy boundaries: video_enhance_v2 vs video_upscale, video_magic_eraser vs video_inpaint (both object/watermark removal), ad_clone_analyze vs video_analyze, and ai_actor_list vs persona_list. Descriptions help somewhat, but an agent must read carefully to pick the right eraser/enhancer or the right actor list.
The dominant pattern is resource_action (image_create, video_generate, persona_list), but it is broken by verb-first names (create_ad_from_product_url, fetch_video_from_link, get_work_status, batch_get_work_status, get_persona_status) and by a version suffix (video_enhance_v2). Readable overall, but the mixed verb placement and the _v2 outlier prevent a higher score.
32 tools is heavy for a single server and pushes well past the comfortable 3-15 range; the surface is a broad menu of one-off AI capabilities. While each tool maps to a real operation, the volume makes discovery and correct selection costly for an agent.
Core lifecycle is covered: generation, editing, enhancement, actors/personas (create/list/delete), ad creation, and async status polling including batch. However, there is no task cancellation, no listing/history of generated works or assets, no persona update, and no asset upload/management, leaving several dead ends for multi-step workflows.
Available Tools
32 toolsad_clone_analyzeCInspect
视频复刻 — 分析
Inputs: clip_end, video_url, clip_start.
ad_clone_generateCInspect
视频复刻 — 生成
Inputs: ratio, prompt, duration, video_url, +1 more.
ai_actor_listDRead-onlyIdempotentInspect
系统演员列表
Inputs: age, pose, limit, gender, +6 more.
ai_actor_performCInspect
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。
Inputs: speed, style, script, actor_id, +5 more.
ai_actor_sayCInspect
系统演员语音生成
Inputs: speed, script, actor_id, stability, +2 more.
batch_get_work_statusCRead-onlyIdempotentInspect
批量查询异步任务状态
Inputs: workspace_ids.
create_ad_from_product_urlCInspect
贴商品链接出广告
Inputs: ad_type, product, duration, language, +4 more.
fetch_video_from_linkAIdempotentInspect
解析平台视频链接,换取可用的视频素材
Inputs: urls (required).
get_persona_statusCRead-onlyIdempotentInspect
查询 Persona 状态
Inputs: actor_id.
get_work_statusCRead-onlyIdempotentInspect
查询异步任务状态
Inputs: workspace_id.
image_createAInspect
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)。
Inputs: model, ratio, prompt, sync_mod, +5 more.
image_cutoutCInspect
图片抠图
Inputs: method, image_url, resolution, callback_id, +3 more.
image_ecommerceDInspect
电商产品图
Inputs: methods, language, resolution, user_input, +6 more.
image_enhanceDInspect
图片增强
Inputs: scale, method, image_url, resolution, +3 more.
image_magic_eraserCInspect
AI 图片消除
Inputs: method, mask_url, quantity, image_url, +6 more.
image_posterCInspect
活动海报图
Inputs: method, language, event_info, resolution, +5 more.
persona_createCInspect
创建自定义 Persona
Inputs: name, photo_url, callback_id, voice_audio_url.
persona_deleteCDestructiveIdempotentInspect
删除自定义 Persona
Inputs: actor_id.
persona_listCRead-onlyIdempotentInspect
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。
Inputs: limit, offset.
video_analyzeCInspect
视频拉片
Inputs: video_url, callback_id, workspace_id.
video_character_swapDInspect
视频换脸
Inputs: image_url, video_url, callback_id, workspace_id.
video_editBInspect
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 暂不支持,请留空。
Inputs: model, ratio, prompt, mask_url, +6 more.
video_enhance_v2DInspect
视频增强
Inputs: method, duration, video_url, resolution, +3 more.
video_extendAInspect
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。
Inputs: model, ratio, prompt, duration, +5 more.
video_generateAInspect
视频生成(文生 / 图生 / 首尾帧 / 多参考媒体)
异步任务;状态和结果都通过 /openapi/v1/work/status 轮询获取(暂不支持 webhook 推送)。
model 必填;各模型的 duration / ratio / resolution / reference_* 取值和上限见请求体表格。
Inputs: model, ratio, prompt, duration, +8 more.
video_inpaintCInspect
视频水印消除
Inputs: video_url, callback_id, workspace_id.
video_lip_syncDInspect
视频对口型
Inputs: prompt, audio_url, avatar_url, callback_id.
video_magic_eraserCInspect
AI 视频消除
Inputs: method, duration, video_url, callback_id, +2 more.
video_motion_controlDInspect
视频动作控制
Inputs: mode, prompt, image_url, video_url, +5 more.
video_subtitleDInspect
视频字幕
Inputs: video_url, style_type, callback_id, workspace_id, +3 more.
video_translateDInspect
视频翻译
Inputs: video_url, callback_id, target_lang, workspace_id.
video_upscaleDInspect
视频超分
Inputs: video_url, callback_id, workspace_id.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI video ads, dubbing in the speaker's own voice, and images and clips from top models.
Video ads for e-commerce: AI agents write, clone and generate ads, plus motion-design and AI videos.
Ready-to-publish ad creatives from an AI assistant: campaigns, image/video/UGC ads, brands, edits.
AI ad generator: make image and video ads for your brand and research the ads competitors run.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceGenerate AI UGC video ads from any product URL in 5 minutes. Realistic AI avatars, natural voiceover, proven ad templates. No actors, no editing, no experience required.1MIT

inReels MCPofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to generate video ads, UGC ads, static image ads, voiceovers, and faceless videos, with tools for quoting, model discovery, asset upload, and run status checks.MIT- AlicenseBqualityBmaintenanceMake UGC-style video ads without filming: tell your AI assistant what to say and get a vertical clip of a realistic actor saying it, ready for TikTok, Reels or Shorts. Pick or describe an actor, choose a voice from samples, and see the price before rendering. It also makes faceless videos from a script or a short brief: narration over an opening animated clip and image scenes.581MIT
- AlicenseAqualityBmaintenanceManage ad campaigns across Meta, Google, and TikTok, create campaigns, analyze performance, spy on competitors, and generate AI creatives.520MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.