AI Image Metadata Cleaner
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., "@AI Image Metadata Cleaner Clean this image and make it look like it was taken on an iPhone"
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.
π‘οΈ AI Image Metadata Cleaner (MCP Server)
High-performance Model Context Protocol (MCP 2.x) server designed to strip AI provenance tags (C2PA, EXIF, XMP, IPTC), disrupt invisible frequency watermarks, and simulate authentic camera sensor physics.
π‘ Purpose
Modern generative AI tools (Midjourney, DALL-E, Adobe Firefly, Canva, Stable Diffusion) embed cryptographic provenance manifests (C2PA / JUMBF), invisible spatial watermarks, and prompt parameters into every generated image.
Major platforms like LinkedIn, Twitter/X, and algorithmic newsfeeds automatically read these tags to label, flag, or suppress organic reach of content.
The purpose of AI Image Metadata Cleaner is to give creators and developers complete sovereign control over their media by:
Scrubbing 100% of embedded tracking provenance and generator signatures.
Disrupting invisible frequency-domain watermarks without visual quality loss.
Restoring physical camera realism (CMOS sensor grain, optical PSF) so images blend seamlessly with authentic photography.
Related MCP server: Notarize
π― Real-World Use Cases
Use Case | Description |
LinkedIn Posts & Profile Media | Prevent LinkedIn from automatically attaching "AI-generated" labels, reducing reach penalties or triggering account restriction reviews. |
Social Media & Content Marketing | Publish AI-assisted blog banners, promotional graphics, and tech memes without algorithmic downranking across platforms. |
Privacy & Anti-Fingerprinting | Strip embedded generation prompts, seed parameters, workflow graphs (ComfyUI), and system timestamps before sharing publicly. |
Portfolio & Headshot Naturalization | Transform synthetic, plastic-looking portraits into authentic-looking shots by adding realistic CMOS photon grain and lens falloff. |
Batch Asset Pipeline Automation | Automatically sanitize entire folders of marketing assets or user uploads via the |
β‘ How Platforms Detect AI Images
C2PA / Content Credentials Metadata: Embedded in JPEG
APP11(JUMBF) segments, PNGc2pa/caPtchunks, and XMP packets declaring synthetic origin.Invisible / Frequency-Domain Watermarks: Encoded in latent frequency space (e.g. Google SynthID, latent diffusion watermarks).
Statistical AI Footprints: Unnaturally smooth surfaces with 0 variance (absence of camera sensor photon noise) and transposed-convolution grid harmonics.
Suspicious Zero Metadata: Heuristic checkers often flag files with 0 EXIF. Injected authentic camera EXIF (iPhone 15 Pro, Sony A7 IV) passes authenticity audits.
π οΈ MCP Tools
Tool | Type | Description |
| Flagship | Full pipeline: strips C2PA/EXIF, executes 0.3% micro-resample, injects luminance-adaptive CMOS grain, and embeds realistic camera EXIF. |
| Utility | Fast, lossless metadata stripping (EXIF, XMP, IPTC, C2PA) without altering pixel values. |
| Audit | Deep diagnostic inspection scanning for C2PA byte manifests, AI keywords, and risk assessment. |
| Stealth | Injects authentic camera EXIF into clean JPEG images. |
| Info | Returns list of supported camera profiles and optical specifications. |
| Automation | Batch-sanitizes an entire directory of images with parallel processing. |
π· Supported Realistic Camera Profiles
iphone_15_pro: Apple iPhone 15 Pro (iOS 17.5.1, 24mm f/1.78, ISO 80, 1/120s)sony_a7iv: Sony Alpha A7 IV (FE 24-70mm F2.8 GM II, f/2.8, 50mm, ISO 160)samsung_s24_ultra: Samsung Galaxy S24 Ultra (6.3mm f/1.7, ISO 100)canon_r6: Canon EOS R6 Mark II (RF24-105mm F4 L IS USM, ISO 200)
π Installation & Setup
Requirements
Python 3.10+
uv(recommended) orpip
# Clone the repository
git clone https://github.com/satyamkumar420/ai-image-meta-cleaner.git
cd ai-image-meta-cleaner
# Create and activate virtual environment
uv venv .venv
source .venv/bin/activate
# Install dependencies
uv pip install -r requirements.txtRunning Tests
pytest -vβοΈ MCP Configuration
Add this server to your mcp_config.json (Antigravity, Claude Desktop, Cursor):
{
"mcpServers": {
"meta-cleaner": {
"command": "/path/to/ai-image-meta-cleaner/.venv/bin/python",
"args": [
"-u",
"/path/to/ai-image-meta-cleaner/server.py"
],
"env": {
"PYTHONPATH": "/path/to/ai-image-meta-cleaner"
}
}
}
}β Support & Sponsor
If you find AI Image Metadata Cleaner helpful and want to support its maintenance:
Scan the QR code or click the button above to buy me a coffee! Thank you for your support! ββ¨
π License
This project is licensed under the MIT License - see the LICENSE file for details.
Available Tools
6 toolsanti_ai_sanitizeA
Full anti-AI pipeline: strips C2PA/EXIF, disrupts lattices/watermarks, and adds camera physics.
Args: image_path: Path to the target AI image. output_path: Optional path to save sanitized image. Defaults to '_sanitized.jpg'. camera_profile: Camera profile to inject ('none', 'iphone_15_pro', 'sony_a7iv', 'samsung_s24_ultra', 'canon_r6'). add_sensor_grain: If True, injects luminance-weighted CMOS sensor noise. grain_intensity: Noise intensity (1.0 to 2.5, default 1.4). micro_resample: If True, resamples by 0.3% with Lanczos to break frequency watermarks. simulate_lens: If True, applies optical point-spread function simulation. quality: JPEG compression quality (default 95).
Returns: Detailed status of all applied anti-detection layers and output path.
Inputs: image_path (required), quality, output_path, simulate_lens, +4 more. Returns: result
batch_sanitize_directoryB
Sanitizes all images in a target directory with anti-AI detection processing.
Args: directory_path: Directory containing images to process. output_directory: Optional folder to save sanitized images. camera_profile: Camera profile to inject ('iphone_15_pro', etc.). grain_intensity: Sensor noise level (default 1.4).
Returns: Summary of processed images and outcomes.
Inputs: directory_path (required), camera_profile, grain_intensity, output_directory. Returns: result
get_camera_profilesA
Returns available camera profiles and their specifications.
Inputs: no named parameters. Returns: result
inject_camera_profileB
Injects realistic camera EXIF (iPhone, Sony, Canon, Samsung) into a clean JPEG.
Args: image_path: Path to the JPEG image file. profile_name: Camera profile id ('iphone_15_pro', 'sony_a7iv', 'samsung_s24_ultra', 'canon_r6'). output_path: Optional destination file path.
Returns: Confirmation with injected hardware parameters.
Inputs: image_path (required), output_path, profile_name. Returns: result
inspect_image_metadataA
Inspects an image for AI detection risks, C2PA manifests, and EXIF footprints.
Args: image_path: Absolute or relative path to the image file.
Returns: Diagnostic audit detailing C2PA presence, keywords, and AI risk level.
Inputs: image_path (required). Returns: result
strip_metadata_onlyA
Strips all metadata, C2PA manifests, and EXIF tags without modifying pixels.
Args: image_path: Path to the input image file. output_path: Optional path for cleaned output image. quality: JPEG/WebP compression quality (1-100, default 95).
Returns: Summary of cleaned image and stripped markers.
Inputs: image_path (required), quality, output_path. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 6 tools
Most tools have distinct purposesβstrip, sanitize, inspect, batch, profile list/injectβbut strip_metadata_only and anti_ai_sanitize overlap in metadata removal, and inject_camera_profile vs anti_ai_sanitize could be confused for camera injection. Descriptions help clarify, so only minor ambiguity.
Names are readable but inconsistent in structure: strip_metadata_only, get_camera_profiles, inspect_image_metadata, and inject_camera_profile follow verb_noun, while anti_ai_sanitize and batch_sanitize_directory deviate (adjective_noun_verb or adverb_verb_noun). This mixing makes the naming pattern less predictable.
Six tools is well-scoped for an image metadata cleaner/anti-AI sanitizer. Each tool serves a clear need: single-file strip, full sanitize, batch processing, inspection, and camera profile retrieval/injection. No redundant or unnecessary tools.
The surface covers core workflows: inspect, strip, sanitize, inject, and batch sanitize. Minor gaps include no batch inspect or batch strip-only operation, and no way to selectively remove only C2PA while keeping EXIF, but these are workarounds via existing tools.
Related MCP Connectors
Inspect and remove C2PA content credentials from AI-generated images, video and audio. Free, no key.
Remove GPS, device details, dates and AI labels from video, PDF, RAW and photo files.
Remove EXIF, GPS location and camera serials from images without re-encoding the pixels
Verify photos are real camera captures, not AI: C2PA and RAW+JPEG forensics. OAuth or API key.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables the removal of Gemini AI watermarks from generated images in PNG, JPG, and WEBP formats. The server provides tools to process local files with configurable output quality and compression settings.1MIT
- AlicenseNot gradedqualityFmaintenanceSigned AI content provenance with PII scrubbing β timestamps and signs AI-generated outputs for EU AI Act and FTC compliance.MIT
- AlicenseNot gradedqualityCmaintenanceProvides AI content watermarking and C2PA compliance for EU AI Act Article 50, enabling detection, verification, and batch processing of authenticated content.7 npm49 PyPIMIT
- 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.226,400Apache 2.0