AI Metadata Cleaner MCP server
Remove hidden metadata from your files by asking your AI assistant:
"Remove the location and camera details from the videos in ~/Downloads/trip"
It removes GPS locations and tracks, phone and camera models, serial numbers, dates, author and
software names, and AI-generation labels from:
- Video: MP4, MOV, M4V, 3GP, MKV, WebM (video and sound are not re-encoded)
- PDF
- Camera RAW: CR2, CR3, NEF, ARW, RAF, RW2, DNG
- Photos: JPEG, PNG, WebP
Each file is sent to the AI Metadata Cleaner server, cleaned,
checked, and saved next to the original as name-clean.ext. Your originals are never changed.
Files are deleted from the server right after cleaning, and the clean copy right after it is
downloaded.
You need
Set up
Claude Desktop — Settings → Developer → Edit Config, then add:
{
"mcpServers": {
"aimetadatacleaner": {
"command": "npx",
"args": ["-y", "aimetadatacleaner-mcp"],
"env": { "AMC_API_KEY": "amc_live_..." }
}
}
}
Claude Code
claude mcp add aimetadatacleaner -e AMC_API_KEY=amc_live_... -- npx -y aimetadatacleaner-mcp
Cursor — add the same block as Claude Desktop to ~/.cursor/mcp.json.
Full guide for every app: https://aimetadatacleaner.com/mcp
Tools
clean_files — clean files or folders (a folder means the supported files directly inside it).
Options: output_dir, image_mode (reencode or strip), keep_pdf_signature.
check_usage — jobs and data used this month.
Each file is one job from your monthly allowance.