mcpField
S
ssave.cc — TikTok & Instagram Downloader

ssave.cc — TikTok & Instagram Downloader

Local
github.com/ssaveccMedia & Design0Updated 8w ago

About ssave.cc — TikTok & Instagram Downloader

An MCP server for extracting and saving TikTok, Instagram, YouTube, and Douyin media to local disk. It offers format selection for video and MP3 downloads, plus thumbnail saving.

Key features

  1. 01Extract media details and formats
  2. 02Download video or MP3 to disk
  3. 03Save thumbnails locally
  4. 04Runs over local stdio

Use cases

  1. 01Save a video from a supported platform
  2. 02Download audio as an MP3
  3. 03Review formats before downloading

MCP support

Exposes `extract_media`, `download_media`, and `get_thumbnail` as tools for MCP clients. It runs locally over stdio and uses the Ssave Open API.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"cc-ssave-tiktok-instagram-downloader": {
"command": "npx",
"args": [
"-y",
"@ssavecc/mcp-server"
],
"env": {
"YOUR_API_KEY": "<YOUR_API_KEY>"
}
}
}
}
Run commandnpx -y @ssavecc/mcp-server
Environment variables to set
YOUR_API_KEYSecretYour API key for the service

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@ssavecc/mcp-server0.1.1

Tools

3

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
urlstringYesTikTok / Instagram / YouTube / Douyin video link
formatenumNoDefaults to video; audio retrieves mp3 only (for YT/IG, call again as needed)video | audio

Details

From the project README

@ssavecc/mcp-server

ssave-mcp-server MCP server Listed on mcpservers.org

Model Context Protocol (MCP) server for Ssave.cc — extract and download TikTok / Instagram / YouTube / Douyin media (HD video without watermark, MP3 audio) directly to your local disk.

Runs locally via stdio, backed by the Ssave Open API (/open/v1). No registration required on the free tier.

Quick Start

npx @ssavecc/mcp-server

Then add it to your MCP client:

Claude Code
claude mcp add ssave -- npx @ssavecc/mcp-server

Or project-level .mcp.json:

{
  "mcpServers": {
    "ssave": { "command": "npx", "args": ["@ssavecc/mcp-server"] }
  }
}
Cursor

Settings → MCP → Add new MCP server:

{
  "mcpServers": {
    "ssave": {
      "command": "npx",
      "args": ["@ssavecc/mcp-server"]
    }
  }
}
Claude Desktop

Edit claude_desktop_config.json:

{
  "mcpServers": {
    "ssave": {
      "command": "npx",
      "args": ["@ssavecc/mcp-server"]
    }
  }
}

Tools

ToolDescription
extract_mediaExtract metadata and available formats from a TikTok / Instagram / YouTube / Douyin URL. Returns an ssv_ token (expires in 5–15 min) plus per-format download URLs.
download_mediaStream the extracted media to local disk (default ~/Downloads/ssave/, override with output_dir). Returns the absolute path and size.
get_thumbnailSave the media thumbnail to local disk (proxied — never exposes the source CDN link).

Typical flow: extract_media(url) → take the returned id → download_media(id, type: "hd" | "watermark" | "mp3").

Environment Variables

All optional:

VariableDefaultDescription
SSAVE_API_BASE_URLhttps://api.ssave.ccOverride for local development (e.g. http://localhost:8000).
SSAVE_API_KEY—Reserved for paid tier (Phase 3): sent as Authorization: Bearer <key>.
SSAVE_OUTPUT_DIR~/Downloads/ssave/Default output directory when output_dir is not passed.

Rate Limits (free tier)

Shared with the Ssave Open API, per IP per UTC day:

OperationLimit
extract10 / day
download50 / day

On 429 rate_limited the tool reports the UTC reset time.

Development

npm install
npm run dev        # run server on stdio (connect with MCP Inspector: npx @modelcontextprotocol/inspector)
npm test           # unit tests (mock fetch)
npm run build      # compile to dist/

Legal

For personal archiving of content you have access to. Respect platform Terms of Service. No bulk downloading. See ssave.cc/privacy.

License

MIT

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.