Official MCP server for creating AI UGC videos with UnrealUGC
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add mcp -- npx -y @unrealugc/mcp{
"mcpServers": {
"mcp": {
"command": "npx",
"args": ["-y", "@unrealugc/mcp"],
"env": {
"UNREALUGC_API_KEY": "<unrealugc_api_key>"
}
}
}
}UNREALUGC_API_KEYMCP Servers overview
# UnrealUGC MCP Server
[](https://www.npmjs.com/package/@unrealugc/mcp)
[](https://github.com/UnrealUGC/mcp/actions/workflows/ci.yml)
The official [Model Context Protocol](https://modelcontextprotocol.io) server for
[UnrealUGC](https://unrealugc.com). It gives MCP-compatible assistants eleven typed tools for
browsing creators and models, estimating credit cost, and generating AI UGC video ads.
This repository contains only the public MCP adapter. The UnrealUGC application and backend
remain private.
## Prerequisites
- Node.js 20 or newer
- An UnrealUGC API key from **Dashboard → Settings → API Keys**
API keys start with `usk_live_` and should be stored in your MCP client's environment settings,
never committed to a repository.
## Local stdio setup
You do not need to install the package globally. MCP clients can launch it with `npx`.
### Claude Desktop
Add this server to your Claude Desktop configuration:
```json
{
"mcpServers": {
"unrealugc": {
"command": "npx",
"args": ["-y", "@unrealugc/mcp"],
"env": {
"UNREALUGC_API_KEY": "usk_live_..."
}
}
}
}
```
### Claude Code
```bash
claude mcp add unrealugc --env UNREALUGC_API_KEY=usk_live_... -- npx -y @unrealugc/mcp
```
### Codex
```toml
[mcp_servers.unrealugc]
command = "npx"
args = ["-y", "@unrealugc/mcp"]
[mcp_servers.unrealugc.env]
UNREALUGC_API_KEY = "usk_live_..."
```
Cursor, Windsurf, OpenClaw, and other stdio MCP clients use the same command and environment
variable.
## Hosted Streamable HTTP setup
Clients that support remote MCP can connect without running a local process:
```text
URL: https://unrealugc.com/api/mcp
Authorization: Bearer usk_live_...
```
See the [MCP setup guide](https://unrealugc.com/docs/mcp) for client-specific instructions.
## Tools
| Tool | Purpose |
| --- | --- |
| `get_me` | Confirm the account, plan, and balance behind an API key |
| `get_credits` | Read subscription and purchased credit pools |
| `list_models` | Browse available video models and capabilities |
| `list_creators` | Browse stock creators and custom avatars |
| `list_voices` | Browse stock and custom voices |
| `list_projects` | Find product and campaign projects |
| `create_project` | Create a project for related generations |
| `list_videos` | Browse generation history with filters and pagination |
| `get_video` | Poll a generation and retrieve its output URL |
| `estimate_video_cost` | Estimate credits from the script before spending |
| `generate_video` | Start an asynchronous video generation |
`generate_video` supports native or selected voices, silent reaction/b-roll clips, per-scene
visual directions, and parallel or sequential multi-clip generation.
## Generation flow
1. Call `list_models` and `list_creators`.
2. Call `estimate_video_cost` with the proposed script.
3. Check `get_credits` if budget matters.
4. Call `generate_video`.
5. Poll `get_video` about every 15 seconds, or use UnrealUGC webhooks for completion events.
## Environment variables
| Variable | Required | Default |
| --- | --- | --- |
| `UNREALUGC_API_KEY` | Yes | — |
| `UNREALUGC_BASE_URL` | No | `https://unrealugc.com` |
| `UNREALUGC_REQUEST_TIMEOUT_MS` | No | `30000` |
`UNREALUGC_BASE_URL` is intended for UnrealUGC development and staging environments.
## Development
```bash
npm ci
npm run check
npm pack --dry-run
```
See [CONTRIBUTING.md](CONTRIBUTING.md) before opening a pull request. Security reports should
follow [SECURITY.md](SECURITY.md).
## Links
- [UnrealUGC MCP overview](https://unrealugc.com/mcp)
- [MCP documentation](https://unrealugc.com/docs/mcp)
- [REST API documentation](https://unrealugc.com/docs/api)
- [UnrealUGC dashboard](https://unrealugc.com/dashboard)
## License
MIT © Next MVP Solutions LLC
What people ask about mcp
What is UnrealUGC/mcp?
+
UnrealUGC/mcp is mcp servers for the Claude AI ecosystem. Official MCP server for creating AI UGC videos with UnrealUGC It has 0 GitHub stars and its last recorded update is dated 2026-08-18.
How do I install mcp?
+
You can install mcp by cloning the repository (https://github.com/UnrealUGC/mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is UnrealUGC/mcp safe to use?
+
Our security agent has analyzed UnrealUGC/mcp and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains UnrealUGC/mcp?
+
UnrealUGC/mcp is maintained by UnrealUGC. The last recorded GitHub activity is dated 2026-08-18, with 0 open issues.
Are there alternatives to mcp?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/unrealugc-mcp)<a href="https://claudewave.com/repo/unrealugc-mcp"><img src="https://claudewave.com/api/badge/unrealugc-mcp" alt="Featured on ClaudeWave: UnrealUGC/mcp" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!