
Vicsee Mcp ServerArt & Culture
Generate, edit, and upscale AI videos and images asynchronously via multiple models with credit-based usage.
Overview
This MCP server enables agents to generate, edit, and upscale AI-created videos and images using various models such as Seedance, Veo, Kling, FLUX, and Nano Banana. It supports asynchronous task handling where generation or upscaling requests return task IDs that agents poll for completion and media URLs. The server requires an API key from vicsee.com and integrates with MCP-compatible clients like Hermes Agent, Claude, Cursor, and OpenClaw. Use it when you need programmatic access to AI media generation and enhancement within an agent workflow.
Use cases
Key features
Quick Install
Automated & IDE SetupCopy the AI prompt to automatically install this server into your coding agent (Claude Code, Cursor, etc.), or use 1-click editor setup below.
Manual Client & Custom JSON ConfigExpand JSON โพ
Install Config Generator
๐ก Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Capabilities & Tool Schemas
Inspect callable tools, capabilities, and parameters exposed to AI agents by Vicsee Mcp Server.
Documentation Overview
VicSee MCP Server
Generate, edit, and upscale AI video & images from any agent โ 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, โฆ) + their credit costs |
vicsee_generate | Text/image โ 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 โ your agent then polls vicsee_get_task until status is completed and reads the
URL from result.url.
Setup
- Get an API key at vicsee.com โ Settings โ API (starts with
sk-). API access requires a paid plan or credit pack. - Add the server to your MCP client config with that key:
That's the whole setup โ drop in your key, and your agent can generate.
Client config locations
- Claude Desktop:
claude_desktop_config.jsonโmcpServers - Cursor: Settings โ MCP โ 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_URLโ override the API base URL (defaults tohttps://vicsee.com/api/v1).
Local development
Point your MCP client at the local build by using "command": "node", "args": ["/abs/path/to/dist/index.js"].
Example agent flow
"Make me a 5-second video of a kitten chasing a laser."
vicsee_list_models(type: video) โ pick e.g.seedance-2-0-text-to-videovicsee_generate(model, prompt, duration: 5) โ{ id, status: "pending" }vicsee_get_task(id) โฆ poll โฆ โ{ status: "completed", result: { url: "https://cdn.vicsee.com/โฆ" } }
Notes
- Result URLs are served from
cdn.vicsee.comโ stable VicSee CDN links. - Each generation costs credits; see
vicsee_list_modelsfor per-model costs andvicsee_get_creditsfor your balance.
License
MIT
Related MCP Servers
View all alternativesFrequently Asked Questions about Vicsee Mcp Server
What is the Vicsee Mcp Server MCP server used for?
Generate, edit, and upscale AI video & images (Seedance, Veo, Kling, FLUX, Nano Banana) from any agent via VicSee.
How do I install Vicsee Mcp Server in Claude Desktop or Cursor?
Copy the client configuration JSON snippet from the installation section above into your claude_desktop_config.json or .cursor/mcp.json file, then restart your AI application.
Is the Vicsee Mcp Server MCP server free and safe to use?
Yes, Vicsee Mcp Server is listed as a free Model Context Protocol server. Always review repository source code and permissions before granting local workspace access to AI agents.