{
  "markdown": "# VicSee MCP Server\n\nGenerate, edit, and upscale AI **video & images** from any agent — [VicSee](https://vicsee.com)\nas a set of [MCP](https://modelcontextprotocol.io) tools.\n\nWorks with **Hermes Agent, Claude (Desktop / Code), Cursor, OpenClaw**, and any MCP-compatible client.\n\n## What your agent can do\n\n| Tool | What it does |\n|------|--------------|\n| `vicsee_list_models` | List available models (Seedance, Veo, Kling, FLUX, Nano Banana, …) + their credit costs |\n| `vicsee_generate` | Text/image → **video or image** with a chosen model |\n| `vicsee_get_task` | Poll a task and get the finished media URL |\n| `vicsee_upscale_image` | Upscale an image |\n| `vicsee_upscale_video` | Upscale a video |\n| `vicsee_get_credits` | Check your credit balance |\n\nGeneration is **asynchronous**: `vicsee_generate` (or `vicsee_upscale_*`) returns a task `id`\nimmediately — your agent then polls `vicsee_get_task` until `status` is `completed` and reads the\nURL from `result.url`.\n\n## Setup\n\n1. Get an API key at **[vicsee.com](https://vicsee.com) → Settings → API** (starts with `sk-`).\n   API access requires a paid plan or credit pack.\n2. Add the server to your MCP client config with that key:\n\n```json\n{\n  \"mcpServers\": {\n    \"vicsee\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@vicsee/mcp-server\"],\n      \"env\": { \"VICSEE_API_KEY\": \"sk-your-key-here\" }\n    }\n  }\n}\n```\n\nThat's the whole setup — drop in your key, and your agent can generate.\n\n### Client config locations\n\n- **Claude Desktop:** `claude_desktop_config.json` → `mcpServers`\n- **Cursor:** Settings → MCP → add server (same `command`/`args`/`env`)\n- **Hermes Agent / OpenClaw:** add to the MCP servers section of your agent config\n- **Claude Code:** `claude mcp add vicsee -e VICSEE_API_KEY=sk-... -- npx -y @vicsee/mcp-server`\n\n### Optional env\n\n- `VICSEE_BASE_URL` — override the API base URL (defaults to `https://vicsee.com/api/v1`).\n\n## Local development\n\n```bash\npnpm install\npnpm build\nVICSEE_API_KEY=sk-... node dist/index.js   # stdio server\n# or run from source: VICSEE_API_KEY=sk-... pnpm dev\n```\n\nPoint your MCP client at the local build by using `\"command\": \"node\", \"args\": [\"/abs/path/to/dist/index.js\"]`.\n\n## Example agent flow\n\n> \"Make me a 5-second video of a kitten chasing a laser.\"\n\n1. `vicsee_list_models` (type: video) → pick e.g. `seedance-2-5-text-to-video` (up to 30s) or `seedance-2-0-text-to-video` (adds 1080p/4K)\n2. `vicsee_generate` (model, prompt, duration: 5) → `{ id, status: \"pending\" }`\n3. `vicsee_get_task` (id) … poll … → `{ status: \"completed\", result: { url: \"https://cdn.vicsee.com/…\" } }`\n\n## Notes\n\n- Result URLs are served from `cdn.vicsee.com` — stable VicSee CDN links.\n- Each generation costs credits; see `vicsee_list_models` for per-model costs and\n  `vicsee_get_credits` for your balance.\n\n## License\n\nMIT\n",
  "bytes": 2821,
  "sha": "b50371a61516bb834c38ed2f1d1b7041f779c63b457f3607974939494199bf23",
  "repo_slug": "vicseeai/vicsee-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_vicseeai_vicsee_mcp_server_4080af46/readme"
}