{
  "markdown": "# avots-mcp\n\nOfficial MCP (Model Context Protocol) server for **[avots.ai](https://avots.ai)** - a multi-provider AI platform.\n\nOne connection gives you:\n\n- 🖼 **Image generation & editing** - Nano Banana (Gemini 3 Pro / 3.1 Flash), GPT-5 Image, FLUX, Recraft (incl. native vector SVG), Ideogram\n- 🎬 **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\n- 🧑‍🎤 **Talking heads & avatars** - saved reusable face identities, talking-avatar videos, vertical AI-vlogs for Shorts / TikTok\n- 🎵 **Music & audio** - ElevenLabs Music, ACE-Step, Stable Audio, TTS narration (incl. cloned voices)\n- 🎨 **Studio templates** - photo-montage reels, vintage travel posters, viral trend recreation with your face\n- 💬 **300+ chat models** - Claude (Sonnet / Opus), GPT-5, Gemini 3, DeepSeek, Sonar, and more - billed through one balance\n\nThe server lives at **`https://mcp.avots.ai/`** and speaks the [MCP `2025-06-18` spec](https://modelcontextprotocol.io/specification/2025-06-18) 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).\n\n## Quick start\n\n1. **Sign up at [avots.ai](https://avots.ai)** and mint an MCP key at [Settings → Integrations](https://app.avots.ai/#/settings/integrations) (it looks like `av_mcp_<48hex>`).\n2. **Pick your client** from the table below and follow the linked guide.\n3. **Try it** - ask your client *\"generate an image of a fox in a snowy forest\"* and watch tokens get spent.\n\n| Client | Guide | Auth model |\n| --- | --- | --- |\n| **Claude.ai web** | [docs/claude-web.md](docs/claude-web.md) | OAuth - paste URL, click Connect, sign in (no token copy-paste) |\n| **Claude Desktop** | [docs/claude-desktop.md](docs/claude-desktop.md) | Bearer token via `mcp-remote` |\n| **Claude Code (CLI)** | [docs/claude-code.md](docs/claude-code.md) | Bearer token via `claude mcp add` |\n| **Cursor** | [docs/cursor.md](docs/cursor.md) | Bearer token via `mcp-remote` |\n| **Cline** | [docs/cline.md](docs/cline.md) | Bearer token via `mcp-remote` |\n| **Any other MCP client** | [docs/tools.md](docs/tools.md) - endpoint + tool list | Bearer header `Authorization: Bearer av_mcp_…` |\n\nReady-to-paste `mcp.json` snippets live under [`examples/`](examples/).\n\n## What's in the server\n\nNineteen tools, all documented in [docs/tools.md](docs/tools.md):\n\n| Tool | Cost | What it does |\n| --- | --- | --- |\n| `check_balance` | free | Current tokens, subscription tier and the full pricing catalog. |\n| `list_models` | free | All active models with per-call cost (filter by `chat`, `image`, `video`, `audio`). |\n| `list_avatars` | free | The user's saved reusable face identities. |\n| `list_trends` | free | The avots Studio catalog of viral templates (face-swap videos, ads, animations). |\n| `check_job` | free | Poll any async job by `job_id`. |\n| `chat` | ~10-1000 ⚡ | Send a prompt to any chat model. Useful for delegating to GPT, DeepSeek, Sonar, etc. |\n| `generate_image` | ~200-500 ⚡ | Sync image gen AND photo editing (`image_urls`). Recraft can return native vector SVG (`format: \"svg\"`, 2x). |\n| `generate_video` | ~200-5000 ⚡ | Async video gen with **two-step confirmation**; supports i2v, multi-photo character refs and motion-reference clips. |\n| `face_swap_video` | ~500-2000 ⚡ | Swap the face in an existing video with a photo (or saved avatar). Two-step. |\n| `edit_video` | ~450 ⚡/sec | Scene edit of an existing clip by text prompt; person, motion and original audio preserved. Two-step. |\n| `lipsync_video` | ~300-600 ⚡ | Re-voice an existing talking video: new text (TTS) or a ready audio track. Two-step. |\n| `create_avatar` | free / ~200-500 ⚡ | Save a reusable face identity from a photo (free) or generate one from a description. |\n| `generate_talking_avatar` | ~600-2500 ⚡ | A portrait speaks your exact text: TTS + lip-sync, quality/fast tiers. Two-step. |\n| `generate_vlog` | preview shows price | Vertical AI-influencer clip for Shorts / TikTok: the server writes the line from your topic. Two-step. |\n| `generate_audio` | ~50-800 ⚡ | Music (ElevenLabs Music, ACE-Step, Stable Audio) or TTS narration incl. cloned voices. Async. |\n| `create_montage` | ~200 ⚡ | Slideshow reel from 4-25 photos: Ken Burns + crossfades + music. |\n| `create_travel_poster` | ~200-500 ⚡ | Face photo → vintage travel poster of any country. Synchronous. |\n| `recreate_trend` | per trend | Put the user's face into a viral template from `list_trends`. |\n| `create_calendar_event` | ~5 ⚡ | Natural language → event in the linked Apple/Google calendar (or an .ics download). |\n\n> **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.\n\n## What you can build\n\nA few things this is actually useful for. Each one chains two or more tools through one connection and one balance.\n\n- **Social ad creative in one prompt** — hero image, animated variant, music bed.\n- **Product-photo angle pack** — one product shot in, four angles + a rotation clip out.\n- **Storyboard to animatic** — four script-driven frames animated into a 12-second rough cut.\n- **Vertical Reels / Shorts factory** — 9:16 clip + matching 15-second music bed, repeatable per video.\n- **Podcast cover art + show notes** — four cover variations and a written episode description for each.\n- **Second-opinion delegation** — forward a tricky problem to a model from a different lineage and compare.\n- **Localized brand assets** — translated copy and locale-tuned visuals across markets.\n\nEach of these flows is written out as a runnable script — exact prompt, tool sequence, model picks, cost — in [`docs/recipes.md`](docs/recipes.md).\n\nCost 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.\n\n## Billing\n\nAll 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.\n\nSee [pricing.avots.ai](https://avots.ai/pricing) for token packs and subscriptions.\n\n## Troubleshooting\n\nCommon cross-client issues (401s, daily caps, two-step video flow, image rendering, `npx` PATH gotchas) are collected in [`docs/troubleshooting.md`](docs/troubleshooting.md). For client-specific setup, see the per-client guide linked in the table above.\n\n## Issues & feedback\n\nOpen an issue here, or write to [hello@avots.ai](mailto:hello@avots.ai). For platform questions (billing, models, web app) the Telegram bot [@AvotsAIbot](https://t.me/AvotsAIbot) is the fastest channel.\n\n## License\n\n[MIT](LICENSE) - feel free to fork the docs, the examples, and anything else here.\n",
  "bytes": 7209,
  "sha": "2d6030ceff113d2d9f2de8cceae75d60dc56e27c9e7f8d0e37df89c3f7df1b4f",
  "repo_slug": "avotsai/avots-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_avotsai_avots_mcp_38c89f26/readme"
}