{
  "markdown": "# Dora Video MCP — AI Video Generation MCP Server\n\n**Dora Video** is a hosted **AI video and image generation MCP server** for\nChatGPT, Claude, Cursor, Google Antigravity and any other Model Context Protocol\nclient. One OAuth-secured connection gives an agent 16 models — Google Veo 3,\nKling 2.6, SeeDance 2, SeeDance 1.5 Pro, Grok Imagine, Nano Banana Pro and\nothers — with the coin cost of each returned **before** anything is generated,\nsorted cheapest first.\n\n```\nhttps://doravideo.com/mcp\n```\n\nBuilt and operated by [Saga Labs](https://aisagalab.com). Full public\nspecification, limitations included: **<https://doravideo.com/ai-video-mcp>**\n\n---\n\n## Why this exists\n\nMost video MCP servers are either a single provider, or raw infrastructure that\nhands your agent a job id and leaves it to build polling, retries and billing.\nDora sits in between: a curated catalogue behind one account and one balance,\nfour tools an agent can reason about in a single pass, and a finished MP4 or\nimage at the end.\n\nThe design bet is that **an agent picks better from a short list**. A tool per\nmodel, or per provider, makes the tool list longer than the task.\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `list_models` | Every model with its live coin cost, max duration, and whether it accepts an image or a video input. **Sorted cheapest first.** |\n| `generate_video` | Text-to-video, image-to-video, or motion transfer from a driving clip. Returns a job id. |\n| `generate_image` | Text-to-image and image editing from reference photos. Returns a job id. |\n| `check_job` | Polls a job and returns the finished file. |\n\nBecause `list_models` publishes prices, this works:\n\n> \"Animate this product photo as a vertical ad. Use the cheapest model that can\n> do it, tell me what it will cost, and wait for me to confirm.\"\n\n## Models\n\n**Video (9):** `grok_1_5`, `seedance_1_5_pro`, `grok_image_to_video`,\n`grok_text_to_video`, `kling_2_6`, `kling_2_6_motion`, `veo_3`,\n`seedance_2_fast`, `seedance_2`\n\n**Image (7):** `z_image`, `google_nano_banana`, `google_nano_banana_edit`,\n`gpt4o_image`, `gpt_image_2`, `nano_banana_2`, `nano_banana_pro`\n\n### Costs\n\n1 Dora coin = 1 provider credit, no multiplier. Dollar figures are the coin\nvalue on the Pro plan ($15 for 1,000 coins). Verified 5 September 2026.\n\n| Model | Configuration | Coins | On Pro |\n|---|---|---:|---:|\n| `z_image` | 1 image | 1 | $0.02 |\n| `google_nano_banana` | 1 image | 4 | $0.06 |\n| `nano_banana_2` | 1K–2K image | 8 | $0.12 |\n| `grok_1_5` | 4s · 480p video, native audio | 10 | $0.15 |\n| `seedance_1_5_pro` | 4s · 480p video | 14 | $0.21 |\n| `nano_banana_pro` | 1K–2K image | 18 | $0.27 |\n| `kling_2_6` | 5s video, no audio | 55 | $0.83 |\n| `veo_3` | 8s video (Veo 3 Fast) | 60 | $0.90 |\n| `seedance_2` | 4s · 480p video | 76 | $1.14 |\n\nLonger durations, higher resolutions and audio scale up. `list_models` is\nalways authoritative; this table is a snapshot.\n\n## Connect it\n\n### Remote (ChatGPT, Claude, Cursor, Antigravity)\n\nAdd `https://doravideo.com/mcp` as a remote MCP server and approve the OAuth\nprompt. OAuth 2.1 with dynamic client registration; no API key to manage.\nStep-by-step guides:\n\n- [ChatGPT](https://doravideo.com/chatgpt)\n- [Claude](https://doravideo.com/claude)\n- [Cursor](https://doravideo.com/cursor)\n- [Google Antigravity](https://doravideo.com/antigravity)\n- [Every other MCP client](https://doravideo.com/connectors)\n\n### Stdio bridge\n\nFor clients that only speak stdio, `bin/dora-mcp.js` in this repo bridges to the\nsame endpoint with an API key from\n[doravideo.com/account](https://doravideo.com/account):\n\n```json\n{\n  \"mcpServers\": {\n    \"dora\": {\n      \"command\": \"node\",\n      \"args\": [\"/path/to/dora-mcp/bin/dora-mcp.js\"],\n      \"env\": { \"DORA_API_KEY\": \"dora_sk_...\" }\n    }\n  }\n}\n```\n\n## What Dora does not do\n\nStated here so nobody discovers it later:\n\n- **No public REST API today.** Access is the web app, the iOS app, or MCP.\n- **No deterministic price router.** `list_models` returns costs cheapest first\n  and the agent chooses; Dora does not choose for it.\n- **`list_models` returns the default configuration cost**, not a quote for\n  every parameter combination.\n- **No publishing or scheduling.** Dora returns files; you post them.\n- Free web accounts get 60 starter credits. Beyond that requires a paid plan or\n  a credit pack.\n\nIf you are building your own high-volume video backend, model infrastructure\nplatforms are a better fit. Dora is a better fit when the goal is a finished\nclip with minimal integration.\n\n## Pricing\n\n| Plan | Monthly | Credits |\n|---|---|---|\n| Pro | $15 | 1,000 |\n| Plus | $49 | 4,000 |\n| Max | $99 | 10,000 |\n\n60 free credits on web signup, no card. Every plan includes every model, every\nresolution, commercial rights and no watermark.\n\n## Also available without an agent\n\nThe same account and balance work on the web at\n[doravideo.com](https://doravideo.com) and on the\n[iPhone app](https://apps.apple.com/app/id6754180384). Android is in review.\n\n## Links\n\n- Specification: <https://doravideo.com/ai-video-mcp>\n- Model catalogue: <https://doravideo.com/models>\n- Studio: <https://aisagalab.com>\n- Support: <https://doravideo.com/support> · sagalabs@proton.me\n\n---\n\nThe MCP server itself is hosted and closed-source. This repository is the public\ndocumentation and the stdio bridge.\n",
  "bytes": 5316,
  "sha": "b233a1adbd14bedf05e4fa4e2b4395a669115c403cf9f24b7eecac8b0cd9763e",
  "repo_slug": "saga-labs/dora-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_saga_labs_dora_mcp_52e64a77/readme"
}