VicSee MCP Server
About
Generate, edit, and upscale AI video & images from any agent — VicSee as a set of MCP tools. Multi-model (Seedance, Veo, Kling, FLUX, Nano Banana), text or image to video or image, with async task polling. Six tools: list models, generate, poll task, upscale image, upscale video,
Details
- Author
- vicseeai
- Downloads
- 449
- Categories
- Media, AI
Jump to
- List available models and their credit costs
- Generate video or image from text or image
- Poll tasks until completion and retrieve media URL
- Upscale both images and videos
- Check your remaining credit balance
- Asynchronous generation with task-based polling
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
VicSee MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Obtain an API key from VicSee (requires a paid plan or credit pack), then add the server to your MCP client’s configuration with the key in the VICSEE_API_KEY environment variable. Use tools like vicsee_generate to start a task, then poll with vicsee_get_task to retrieve the finished media URL.
vicsee_list_models
List available VicSee models with their capabilities and credit costs. Call this first to find a model id to pass to vicsee_generate. Optionally filter by media type.
vicsee_generate
Create an AI image or video with VicSee. Generation is ASYNCHRONOUS: this returns a task `id` immediately, then poll `vicsee_get_task` with that id until status is "completed" (the result URL appears in result.url) or "failed". Use vicsee_list_models to pick a `model` and see its valid options. For image-to-video / image-to-image, pass source images in `image_urls`. For reference-to-video models (e.g. "seedance-2-5-reference-to-video"), pass references in reference_image_urls / reference_video_urls / reference_audio_urls and refer to them positionally in the prompt as @Image1, @Image2, … For native 2K output at the best value per second use the "minimax-h3-*" models (MiniMax H3, also called Hailuo 03): 4-15s, 768P/2K, always-on stereo audio, billed per second (25 credits/s at 768P, 40 at 2K). Note "minimax-h3-image-to-video" takes the first frame in image_urls[0] and an optional last frame in image_urls[1], and has NO aspect_ratio parameter — the ratio follows the frames; "minimax-h3-reference-to-video" requires at least one image OR video reference (audio alone is rejected) and accepts at most 5 reference images. For clips longer than 15 seconds use the "seedance-2-5-*" models, which generate up to 30 seconds (480p/720p only, no 1080p or 4K); the "seedance-2-0-*" models cap at 15 seconds but add 1080p and 4K. Note that supplying a video reference switches billing to per-second across input + output, so a long reference clip costs considerably more than the duration table suggests — check credits in vicsee_list_models before generating. IMAGE inputs (image_urls, reference_image_urls) may be a public https URL, a local file path (this server reads and base64-encodes it for you), or a base64 data URI. VIDEO/AUDIO inputs (reference_video_urls, reference_audio_urls) must be public https URLs. For video-edit models (e.g. "happyhorse-video-edit"), pass the source clip in video_url and optionally set audio_setting ("auto" or "origin"). Input images must have an aspect ratio between 0.4 and 2.5 (width÷height) and at most 36MP — wide-strip composites (e.g. 3:1) are rejected; use a 2×2 grid layout instead. On "failed" tasks, read error.key and error.message from vicsee_get_task — they state the actual reason (do not guess).
vicsee_get_task
Poll a generation or upscale task by its id. status is one of "pending" | "processing" | "queued" | "completed" | "failed". When "completed", the media URL is in result.url (videos/images) or result.songs (music). When "failed", details are in error. Poll every few seconds until completed or failed.
vicsee_upscale_image
Upscale a publicly accessible image (JPEG/PNG/WebP). Asynchronous: returns a task id — poll vicsee_get_task until completed. upscale_factor defaults to "2" (max "4"). Credits are tiered by OUTPUT size (input megapixels × factor²): ≤24MP = 20, ≤48MP = 40, ≤96MP = 80; outputs above 96MP are rejected.
vicsee_upscale_video
Upscale a publicly accessible video (MP4/MOV/MKV, up to 60s). Asynchronous: returns a task id — poll vicsee_get_task until completed. upscale_factor defaults to "2".
vicsee_get_credits
Get the current VicSee credit balance for the configured API key.
vicsee_upload
Upload a LOCAL file (image, video, or audio) from this machine and get back a public https URL. Use the returned url as an input for vicsee_generate — e.g. drop it into reference_image_urls for a reference-to-video storyboard, or image_urls for image-to-video. PREFER this over inline base64 for references: large base64 strings get truncated in tool-call output and the model rejects them. The file uploads directly to storage; only its public URL comes back.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"vicsee mcp server": {
"vicsee": {
"command": "npx",
"args": [
"-y",
"@vicsee/mcp-server"
],
"env": {
"VICSEE_API_KEY": "sk-your-key-here"
}
}
}
}
}McpServers
{
"vicsee": {
"command": "npx",
"args": [
"-y",
"@vicsee/mcp-server"
],
"env": {
"VICSEE_API_KEY": "sk-your-key-here"
}
}
}VicSee MCP Server
Generate, edit, and upscale AI video & images from any agent — VicSee
as a set of MCP tools.
Works with Hermes Agent, Claude (Desktop / Code), Cursor, OpenClaw, and any MCP-compatible client.
What your agent can do
| Tool | What it does |
|------|--------------|
| vicsee_list_models | List available models (Seedance, Veo, Kling, FLUX, Nano Banana, …) + their credit costs |
| vicsee_generate | Text/image → video or image with a chosen model |
| vicsee_get_task | Poll a task and get the finished media URL |
| vicsee_upscale_image | Upscale an image |
| vicsee_upscale_video | Upscale a video |
| vicsee_get_credits | Check your credit balance |
Generation is asynchronous: vicsee_generate (or vicsee_upscale_*) returns a task id
immediately — your agent then polls vicsee_get_task until status is completed and reads the
URL from result.url.
Setup
1. Get an API key at vicsee.com → Settings → API (starts with sk-).
API access requires a paid plan or credit pack.
2. Add the server to your MCP client config with that key:
{
"mcpServers": {
"vicsee": {
"command": "npx",
"args": ["-y", "@vicsee/mcp-server"],
"env": { "VICSEE_API_KEY": "sk-your-key-here" }
}
}
}
That's the whole setup — drop in your key, and your agent can generate.
Client config locations
- Claude Desktop: claude_desktop_config.json → mcpServers
- Cursor: Settings → MCP → add server (same command/args/env)
- Hermes Agent / OpenClaw: add to the MCP servers section of your agent config
- Claude Code: claude mcp add vicsee -e VICSEE_API_KEY=sk-... -- npx -y @vicsee/mcp-server
Optional env
- VICSEE_BASE_URL — override the API base URL (defaults to https://vicsee.com/api/v1).
Local development
```bash
pnpm install
pnpm build
VICSEE_API_KEY=sk-... node dist/index.js # stdio server
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
