avots

io.github.avotsai由 GitHub 账号 avotsai 发布v1.0.0更新于 Nov 2, 2026

Image, video, audio, face-swap, talking avatars and chat across 300+ AI models, one balance.

已验证Streamable HTTP可网页运行媒体与设计AI 与机器学习

概览

AI 生成的概览

avots.ai 的远程 MCP 服务器，让助手用 300+ 个 AI 模型生成图片、视频、音频、数字人形象和对话，统一从一份余额计费。

可以做什么
  • 生成和编辑图片（含矢量 SVG 输出），并异步生成视频片段
  • 对已有视频换脸、按文字改场景、重新配音，以及制作口播数字人和竖屏 vlog
  • 生成音乐与语音旁白（含克隆音色），以及照片轮播短片和旅行海报
  • 与 300+ 对话模型聊天，把问题转交给其他模型系列
  • 查询余额、模型价格、已保存的人脸形象、热门模板和异步任务状态
  • 用自然语言创建日历事件
适用场景
适合希望用一个连接完成多模型媒体创作与对话的场景，例如社交广告素材、商品图多角度、Shorts/TikTok 竖屏短片、播客封面，或让另一家模型给出第二意见，而不必逐个接入各家服务。
运行要求
远程 Streamable HTTP 端点 mcp.avots.ai，无需本地安装。需要 avots.ai 账号，以及在 Settings → Integrations 生成的 MCP API 密钥，通过 Authorization Bearer 请求头传入，或对支持 OAuth 的客户端直接登录。付费工具需要账户余额。
安装前请注意
除免费的查询类工具外，每次调用都会从 avots 余额扣除 token，单张图片约 200，长时高清视频片段可达约 5000；视频工具采用两步确认以避免意外消费。API 密钥属于机密，不要写入共享配置。提示词、照片和视频会发送到 avots.ai 及其上游模型供应商，生成内容可能被保存为人脸形象或模板。

安装

在 SourceWeft 中

  1. 打开 控制台中的 avots，将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.avotsai%2Favots-mcp/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "avots": {
      "type": "http",
      "url": "https://mcp.avots.ai/"
    }
  }
}

README

avots-mcp

Official MCP (Model Context Protocol) server for avots.ai - a multi-provider AI platform.

One connection gives you:

  • 🖼 Image generation & editing - Nano Banana (Gemini 3 Pro / 3.1 Flash), GPT-5 Image, FLUX, Recraft (incl. native vector SVG), Ideogram
  • 🎬 Video generation & editing - Veo 3.1, Seedance 2.0, Kling v3.0 Pro, Sora 2 Pro, Grok Imagine, Gemini Omni Flash (async, 1-8 min); plus scene edit, face swap and lip-sync re-voicing of existing clips
  • 🧑‍🎤 Talking heads & avatars - saved reusable face identities, talking-avatar videos, vertical AI-vlogs for Shorts / TikTok
  • 🎵 Music & audio - ElevenLabs Music, ACE-Step, Stable Audio, TTS narration (incl. cloned voices)
  • 🎨 Studio templates - photo-montage reels, vintage travel posters, viral trend recreation with your face
  • 💬 300+ chat models - Claude (Sonnet / Opus), GPT-5, Gemini 3, DeepSeek, Sonar, and more - billed through one balance

The server lives at https://mcp.avots.ai/ and speaks the MCP 2025-06-18 spec over Streamable HTTP. Tools are billed per call against your avots balance (same balance you'd see on the web app or the Telegram bot).

Quick start

  1. Sign up at avots.ai and mint an MCP key at Settings → Integrations (it looks like av_mcp_<48hex>).
  2. Pick your client from the table below and follow the linked guide.
  3. Try it - ask your client "generate an image of a fox in a snowy forest" and watch tokens get spent.
ClientGuideAuth model
Claude.ai webdocs/claude-web.mdOAuth - paste URL, click Connect, sign in (no token copy-paste)
Claude Desktopdocs/claude-desktop.mdBearer token via mcp-remote
Claude Code (CLI)docs/claude-code.mdBearer token via claude mcp add
Cursordocs/cursor.mdBearer token via mcp-remote
Clinedocs/cline.mdBearer token via mcp-remote
Any other MCP clientdocs/tools.md - endpoint + tool listBearer header Authorization: Bearer av_mcp_…

Ready-to-paste mcp.json snippets live under examples/.

What's in the server

Nineteen tools, all documented in docs/tools.md:

ToolCostWhat it does
check_balancefreeCurrent tokens, subscription tier and the full pricing catalog.
list_modelsfreeAll active models with per-call cost (filter by chat, image, video, audio).
list_avatarsfreeThe user's saved reusable face identities.
list_trendsfreeThe avots Studio catalog of viral templates (face-swap videos, ads, animations).
check_jobfreePoll any async job by job_id.
chat~10-1000 ⚡Send a prompt to any chat model. Useful for delegating to GPT, DeepSeek, Sonar, etc.
generate_image~200-500 ⚡Sync image gen AND photo editing (image_urls). Recraft can return native vector SVG (format: "svg", 2x).
generate_video~200-5000 ⚡Async video gen with two-step confirmation; supports i2v, multi-photo character refs and motion-reference clips.
face_swap_video~500-2000 ⚡Swap the face in an existing video with a photo (or saved avatar). Two-step.
edit_video~450 ⚡/secScene edit of an existing clip by text prompt; person, motion and original audio preserved. Two-step.
lipsync_video~300-600 ⚡Re-voice an existing talking video: new text (TTS) or a ready audio track. Two-step.
create_avatarfree / ~200-500 ⚡Save a reusable face identity from a photo (free) or generate one from a description.
generate_talking_avatar~600-2500 ⚡A portrait speaks your exact text: TTS + lip-sync, quality/fast tiers. Two-step.
generate_vlogpreview shows priceVertical AI-influencer clip for Shorts / TikTok: the server writes the line from your topic. Two-step.
generate_audio~50-800 ⚡Music (ElevenLabs Music, ACE-Step, Stable Audio) or TTS narration incl. cloned voices. Async.
create_montage~200 ⚡Slideshow reel from 4-25 photos: Ken Burns + crossfades + music.
create_travel_poster~200-500 ⚡Face photo → vintage travel poster of any country. Synchronous.
recreate_trendper trendPut the user's face into a viral template from list_trends.
create_calendar_event~5 ⚡Natural language → event in the linked Apple/Google calendar (or an .ics download).

About the two-step video flow. Video is the most expensive tool. To avoid surprise spend, generate_video returns a preview card the first time it's called (no submit, no reserve). The client (e.g. Claude) shows the cost + alternative models with prices and asks the user. The user confirms, the client re-calls with the chosen model + confirmed: true, and only then does the job get submitted. On submit error the server returns the same alternatives card - it never silently swaps to a pricier model.

What you can build

A few things this is actually useful for. Each one chains two or more tools through one connection and one balance.

  • Social ad creative in one prompt — hero image, animated variant, music bed.
  • Product-photo angle pack — one product shot in, four angles + a rotation clip out.
  • Storyboard to animatic — four script-driven frames animated into a 12-second rough cut.
  • Vertical Reels / Shorts factory — 9:16 clip + matching 15-second music bed, repeatable per video.
  • Podcast cover art + show notes — four cover variations and a written episode description for each.
  • Second-opinion delegation — forward a tricky problem to a model from a different lineage and compare.
  • Localized brand assets — translated copy and locale-tuned visuals across markets.

Each of these flows is written out as a runnable script — exact prompt, tool sequence, model picks, cost — in docs/recipes.md.

Cost ranges from ~200⚡ for a single image to ~5000⚡ for a 10-second 1080p Kling Pro clip — run list_models (free) at any time for live per-call prices.

Billing

All tool calls bill against your avots balance, just like the web app and Telegram bot. No separate metering. Daily USD cap (set in Settings) and per-key rate limits apply.

See pricing.avots.ai for token packs and subscriptions.

Troubleshooting

Common cross-client issues (401s, daily caps, two-step video flow, image rendering, npx PATH gotchas) are collected in docs/troubleshooting.md. For client-specific setup, see the per-client guide linked in the table above.

Issues & feedback

Open an issue here, or write to [email protected]. For platform questions (billing, models, web app) the Telegram bot @AvotsAIbot is the fastest channel.

License

MIT - feel free to fork the docs, the examples, and anything else here.

来源：README.md，提交 32fe5c1

工具

0
该服务器需要登录，因此 SourceWeft 无法在没有账号的情况下读取其工具，也未收录。已连接账号所能看到的内容可能因账号及其权限而异。

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分