F
licenseNot graded
qualityD
maintenanceAutomatically detects and obfuscates sensitive data (PII, secrets, etc.) before Claude processes it, with lossless restoration for client deliverables.
6
-
strip-ai-metadata-mcp
by onsecrethunt
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@strip-ai-metadata-mcp Strip the GPS location from the photos in my Downloads folder"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
strip-ai-metadata
Remove hidden metadata from photos, videos, PDFs and camera RAW files: GPS location, camera and serial numbers, author names, dates, XMP/IPTC, C2PA Content Credentials and AI prompts (Stable Diffusion, ComfyUI, Midjourney, ChatGPT, Firefly).
Lossless. Metadata is cut out or blanked in place, so image pixels, video streams and RAW sensor data are untouched.
Local. Nothing is uploaded.
Use it three ways: an MCP server for AI assistants, a CLI, or a Node library.
This is the engine behind the free browser tools at stripaimetadata.com.
Package | What it is |
A free MCP server for Claude, Cursor and VS Code: "remove the location from the photos in my Downloads folder" | |
CLI and Node library: |
Quick start: Claude Desktop
{
"mcpServers": {
"strip-ai-metadata": { "command": "npx", "args": ["-y", "strip-ai-metadata-mcp"] }
}
}There are more setups (Claude Code, Cursor, VS Code) in the MCP README and at stripaimetadata.com/mcp.
Related MCP server: docuprivado
Supported formats
Kind | Formats | Removed |
Photos | JPG, PNG, WebP, AVIF, HEIC | EXIF, GPS, XMP, IPTC, C2PA, PNG text chunks (prompts, ComfyUI workflows), comments, trailing data |
Video | MP4, MOV, M4V, 3GP | GPS and GPS tracks, device, dates, C2PA, XMP, GoPro and DJI telemetry |
Author, title, software, dates, XMP, page metadata, EXIF inside embedded photos, old revisions | ||
RAW | CR2, CR3, NEF, ARW, DNG, RAF, RW2, ORF, PEF | GPS, body and lens serials, owner, copyright, dates, XMP, IPTC. Make, model and maker notes are kept so raw editors still read the file. |
Layout
src/lib/meta/ image engine (JPEG, PNG, WebP, HEIC/AVIF parsing, lossless stripping, AI and C2PA detection)
src/lib/raw.ts RAW engine (in-place blanking; same size, sensor data untouched)
src/lib/pdf.ts PDF engine
src/lib/video.ts MP4/MOV engine (edits boxes in place, no re-encode)
packages/ npm packages that bundle the engine
scripts/ testsDevelop
npm install
npm run build # builds packages/*/dist
npm test # RAW engine testsMIT licensed.
Available Tools
2 toolsclean_filesRemove metadata from filesA
Removes hidden metadata from photos (JPG, PNG, WebP, AVIF, HEIC), videos (MP4, MOV), PDFs and camera RAW files (CR2, CR3, NEF, ARW, DNG, RAF, RW2, ORF, PEF): GPS location, camera and serial numbers, owner and author names, dates, XMP/IPTC, C2PA Content Credentials and AI prompts. Works on files or folders on this computer. Originals are not changed: a clean copy is saved as name-clean.ext unless in_place is true. Runs locally; nothing is uploaded.
Inputs: paths (required), mode, in_place, recursive, +2 more.
inspect_filesShow hidden metadata in filesARead-only
Lists what photos, videos, PDFs and RAW files reveal without changing them: GPS location, camera, serial numbers, author, dates, C2PA Content Credentials, AI generator tags and AI prompts. Use it to check a file before sharing or to confirm a clean copy is clean.
Inputs: paths (required), recursive.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A4/5.0
Scored across 2 tools
Disambiguation5/5
The two tools are cleanly opposed: clean_files mutates files by stripping metadata, while inspect_files only reports metadata without changing anything. Descriptions explicitly cross-reference the pair (inspect to confirm a clean copy is clean), so an agent can never mistake one for the other.
Naming Consistency5/5
Both names follow the same verb_noun snake_case convention (clean_files, inspect_files) and share the _files noun, giving a predictable, uniform pattern.
Tool Count4/5
Two tools is on the thin side of the typical range, but for a focused local metadata-stripping utility the inspect+clean pairing is exactly the necessary surface with nothing extraneous. It is minimal rather than bloated.
Completeness4/5
The domain lifecycle is covered: inspect before sharing, clean, then inspect again to verify. Minor gaps exist, such as no selective per-tag removal or dry-run/batch summary report, but agents can work around these by re-inspecting cleaned output.
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues
Related MCP Connectors
Remove GPS, device details, dates and AI labels from video, PDF, RAW and photo files.
Inspect and remove C2PA content credentials from AI-generated images, video and audio. Free, no key.
Inspect and strip EXIF, XMP, IPTC, C2PA, PDF info, and Word properties.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Related MCP Servers
docuprivadoofficial
AlicenseNot gradedqualityBmaintenanceEnables Claude Desktop to redact and count personal data in PDFs and images, strip hidden metadata from photos, anonymize Word and text files, prepare watermarked ID copies, and compare contract versions using only user-approved local folders. All processing runs offline on the user's computer, creating new copies instead of modifying or deleting the originals.Apache 2.0- AlicenseAqualityBmaintenanceEnables Claude Code, Cursor, Codex and other MCP clients to generate and edit images and videos directly in a project using AI subscriptions the user already pays for, without API keys or extra billing. Also provides local media tools such as background removal, video editing for social formats, and automatic resizing and optimization of results.25Apache 2.0
- AlicenseCqualityAmaintenanceIdentify and remove AI provenance metadata (C2PA, EXIF, IPTC, XMP, TC260), visible AI-generator labels and supported invisible watermarks from images and video you generated yourself. Runs locally over stdio with uvx.242,266 PyPI6,357Apache 2.0