mcpField
U
UGC Fans

UGC Fans

Remote
ugc.fansMedia & Design0Updated 3w ago

About UGC Fans

UGC Fans is a remote MCP service for creating marketing media from an AI assistant, including website-based short films, ads, images, and videos. It also processes clips in a UGC Fans library and quotes credits before paid generations.

Key features

  1. 01Create launch films from websites
  2. 02Make template-based UGC-style ads
  3. 03Generate images and videos from prompts
  4. 04Trim, caption, and transcribe clips
  5. 05Reformat footage and add branding
  6. 06Quote credits before paid generation

Use cases

  1. 01Make a launch film for a website
  2. 02Create a scripted, voiced product ad
  3. 03Generate marketing images or videos from text
  4. 04Prepare and share finished library clips

MCP support

It exposes media creation and editing tools to clients through a remote Streamable HTTP MCP server. Calls are sent over HTTPS to UGC Fans; all but template search and model listings require OAuth, and paid generations are quoted in credits first.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.ugc.fans/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

30
ParameterTypeRequiredDescription
querystringNoWords to look for in names and descriptions, such as "testimonial" or "product video". Leave out to list everything.

Details

From the project README

UGC Fans

Make marketing media from inside your AI assistant. This plugin connects Claude Code, Codex, ChatGPT, Cursor, VS Code and Gemini CLI to the UGC Fans server at https://mcp.ugc.fans/mcp and adds four skills that tell the assistant how to use it: launch-film, ugc-ad, finish-clip and credits.

What it does

  • Photographs a website and makes a short launch film from it, in landscape, vertical or square.
  • Makes a UGC-style ad for a product from a template, with a script, a person and a voice.
  • Makes images and short video clips from a prompt.
  • Trims, captions, reformats, brands and transcribes footage you already have in your UGC Fans library, and shares finished files by link.

What it runs and what it sends

  • Nothing runs on your machine. The plugin is Markdown and JSON: one remote server entry and four skills. It has no scripts, hooks, commands or local servers, and it installs no packages.
  • Each tool call goes over HTTPS to https://mcp.ugc.fans with the arguments the assistant fills in: the website addresses you ask it to capture, the text for scripts and ads, file paths in your UGC Fans library and the options you choose. UGC Fans fetches and photographs the websites you name.
  • Searching the template catalogue and listing models work without an account. Everything else asks you to sign in at ugc.fans through the standard OAuth flow. The plugin holds no key, token or password in any file.

Credits

Generating images, video and ads spends credits from your UGC Fans account, and each one is quoted before anything is made. Website captures, launch films, clip finishing and transcripts run on UGC Fans' own compute and spend no credits. Plans and credits are described at https://ugc.fans/pricing.

Install

  • Claude Code: claude mcp add --transport http ugcfans https://mcp.ugc.fans/mcp, or the plugin from this repository's own marketplace: claude plugin marketplace add ugcfans/gpt-plugin then claude plugin install ugcfans@ugcfans.
  • Codex: codex mcp add ugcfans --url https://mcp.ugc.fans/mcp, then codex mcp login ugcfans.
  • Gemini CLI: gemini extensions install https://github.com/ugcfans/gpt-plugin.
  • Other clients: add https://mcp.ugc.fans/mcp as a remote Streamable HTTP server.

License

MIT. See LICENSE.

Source: https://github.com/ugcfans/gpt-plugin, published from the UGC Fans product tree; a change lands here with the ship that made it.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.