About GetVidFB Downloader
GetVidFB Downloader is a hosted MCP server for AI assistants that retrieves direct download links for public Facebook, TikTok, and Pinterest media. Its read-only tools return available media variants and metadata; private posts and Facebook Stories are unsupported.
Key features
- 01Facebook video, reel, and photo links
- 02TikTok video links without watermark
- 03Pinterest video, image, and GIF links
- 04Media metadata and track variants
Use cases
- 01Retrieve an HD Facebook reel link
- 02Get a TikTok video link and music track
- 03Find media links for a Pinterest pin
MCP support
The remote MCP server is available over Streamable HTTP at `https://api.getvidfb.com/mcp`. It exposes three read-only tools for retrieving download links for public posts; an API key is needed for tool calls.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.getvidfb.com/mcpclaude mcp add --transport http com-getvidfb-downloader https://api.getvidfb.com/mcp{"mcpServers":{"com-getvidfb-downloader":{"type":"http","url":"https://api.getvidfb.com/mcp"}}}Open in Cursor{"servers":{"com-getvidfb-downloader":{"type":"http","url":"https://api.getvidfb.com/mcp"}}}Open in VS Code{"mcpServers":{"com-getvidfb-downloader":{"type":"http","url":"https://api.getvidfb.com/mcp"}}}{"mcpServers":{"com-getvidfb-downloader":{"serverUrl":"https://api.getvidfb.com/mcp"}}}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.
https://api.getvidfb.com/mcpAuth requiredTools
Details
From the project READMEGetVidFB MCP Server
Remote Model Context Protocol server that gives AI assistants (Claude, ChatGPT, Cursor, VS Code, Windsurf...) direct download links for public Facebook, TikTok and Pinterest posts.
- Endpoint:
https://api.getvidfb.com/mcp(Streamable HTTP) - MCP Registry:
com.getvidfb/downloader - Website: https://getvidfb.com
This repository holds the server's public metadata and docs. The server itself is hosted, so there is nothing to install.
Tools
| Tool | Input | Returns |
|---|---|---|
facebook_download_links | url of a public Facebook video, reel, watch/share link or photo post | SD/HD MP4 with audio, separate video/audio tracks, thumbnail, title, duration |
tiktok_download_links | url of a public TikTok video | No-watermark HD/SD MP4, music track, cover, title, author |
pinterest_download_links | url of a pin or Idea Pin (pinterest.com, pin.it) | Videos, images and GIFs of every page |
All tools are read-only. Private posts and Facebook Stories are not supported. Links point at the platforms' CDNs and expire after a few hours. Only download content you own or have permission to use.
Get an API key
- Create a free account at https://getvidfb.com/auth/register
- Copy your key (
gvfb_...) from the dashboard
Free plan: 50 tool calls per day, reset at 00:00 UTC. initialize and tools/list work without a key.
The key can be sent as any of:
X-API-Key: gvfb_...Authorization: Bearer gvfb_...https://api.getvidfb.com/mcp?api_key=gvfb_...(for clients that only accept a URL)
Setup
Claude Code
claude mcp add --transport http getvidfb https://api.getvidfb.com/mcp --header "X-API-Key: gvfb_YOUR_KEY"
Cursor, VS Code, Windsurf, Claude Desktop
{
"mcpServers": {
"getvidfb": {
"url": "https://api.getvidfb.com/mcp",
"headers": { "X-API-Key": "gvfb_YOUR_KEY" }
}
}
}
Claude.ai / ChatGPT custom connector
Add a custom connector with the URL https://api.getvidfb.com/mcp?api_key=gvfb_YOUR_KEY.
Example
Get me the HD download link for https://www.facebook.com/reel/29099013063058043
The assistant calls facebook_download_links and gets JSON like:
{
"success": true,
"source": "FB-Reel",
"title": "...",
"thumbnail": "https://scontent...jpg",
"duration": 15,
"links": { "sd": "https://video...mp4", "hd": "https://video...mp4", "audio": "https://video...mp4" }
}
License
MIT
Comments
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.