avotsai/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_ ).
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.
| Client | Guide | Auth model |
| --- | --- | --- |
| **Claude.ai web** | docs/claude-web.md | OAuth - paste URL, click Connect, sign in (no token copy-paste) |
| **Claude Desktop** | docs/claude-desktop.md | Bearer token via mcp-remote |
| **Claude Code (CLI)** | docs/claude-code.md | Bearer token via claude mcp add |
| **Cursor** | docs/cursor.md | Bearer token via mcp-remote |
| **Cline** | docs/cline.md | Bearer token via mcp-remote |
| **Any other MCP client** | docs/tools.md - endpoint + tool list | Bearer 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:
| Tool | Cost | What it does |
| --- | --- | --- |
| check_balance | free | Current tokens, subscription tier and the full pricing catalog. |
| list_models | free | All active models with per-call cost (filter by chat, image, video, audio). |
| list_avatars | free | The user's saved reusable face identities. |
| list_trends | free | The avots Studio catalog of viral templates (face-swap videos, ads, animations). |
| check_job | free | Poll 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 ⚡/sec | Scene 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. |