
Filewash
- Updated June 9, 2026
- cassilup/filewash-api
Filewash is a MCP server that provides privacy-first PDF, image, metadata, and background-removal tools to AI agents.
About
Filewash is a privacy-first MCP server that gives coding agents structured tools for PDF and image work, metadata stripping, and background removal without defaulting to opaque third-party upload flows. developers automating content pipelines, onboarding PDFs, or sanitizing assets before launch benefit when the agent can invoke file ops through a single stdio package rather than ad-hoc shell scripts. The catalog positions it on the build shelf under agent-tooling because most installs happen while you wire agent workflows or batch-process assets, though the same tools support security hygiene (EXIF removal) and content prep. Version 0.1.0 indicates an early API surface—verify tool names and limits in the upstream filewash-api repo before production batch jobs. It complements generic filesystem skills with opinionated media and privacy operations; it does not replace a full DAM, OCR stack, or legal redaction review.
- Privacy-first file operations designed for AI agents (local-oriented workflow)
- PDF operations for docs and export pipelines
- Image operations including background removal
- Metadata scrubbing before publishing screenshots or user uploads
- Stdio MCP via npm @fixpixel/filewash-api (v0.1.0), Node runtime
Filewash by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add filewash -- npx -y @fixpixel/filewash-apiAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | @fixpixel/filewash-api |
|---|---|
| Transport | STDIO |
| Auth | None |
| Last updated | June 9, 2026 |
| Repository | cassilup/filewash-api ↗ |
What it does
Let your agent scrub metadata, edit PDFs and images, and remove backgrounds locally without shipping files to random cloud APIs.
Who is it for?
Privacy-conscious developers who want agent-driven asset prep for docs sites, portfolios, and user-generated content features.
Skip if: Skip if you need enterprise DAM, legal-grade redaction, or heavy video transcoding without checking Filewash’s current tool coverage.
What you get
Your agent can run metadata scrubbing, PDF/image ops, and background removal through a dedicated stdio MCP instead of improvised unsafe commands.
- Agent-invokable PDF and image transformation and cleanup
- Metadata-reduced assets safe for public repos and marketing pages
- Background-removed images for UI mocks and storefront content
By the numbers
- MCP server version 0.1.0; npm identifier @fixpixel/filewash-api
- Stdio transport with Node runtimeHint
- Four capability areas stated: PDF ops, image ops, metadata scrubbing, background removal
README.md
filewash — privacy-first file tools for AI agents
The file-processing layer for agents and apps that can't send files to a third party. Compress, convert, resize, merge/split PDFs, strip metadata, and remove backgrounds — exposed as an MCP server, a metered REST API, and an npm SDK. Zero-retention by default: files are processed in memory and never stored or logged.
Built from filewash.app's client-side WASM tools. Same logic, now callable by your agents.
Why this exists
Every other file-tools API and MCP server is a wrapper around an upload-to-server service. That's a non-starter for legal, healthcare, finance, and any GDPR-bound workflow — and it's a liability when you're piping documents into an LLM. filewash is the one built around not keeping your files, with two tools nobody else ships as an MCP: background removal and metadata scrubbing.
MCP server (Claude Desktop, Cursor, Claude Code)
// claude_desktop_config.json → mcpServers
{
"filewash": { "command": "node", "args": ["/path/to/filewash-api/src/mcp/server.js"] }
}
Your agent now has 11 tools. Ask it: "strip the location metadata from these photos before I upload them" or "merge these contracts and rotate the scanned pages."
REST API
# discover
curl https://api.filewash.app/v1/tools
# strip EXIF/GPS from a photo (returns the cleaned image)
curl -X POST https://api.filewash.app/v1/tools/image_strip_metadata \
-H "Authorization: Bearer $FILEWASH_KEY" \
-F 'files=@photo.jpg' -o clean.jpg
# merge PDFs
curl -X POST https://api.filewash.app/v1/tools/pdf_merge \
-H "Authorization: Bearer $FILEWASH_KEY" \
-F 'files=@a.pdf' -F 'files=@b.pdf' -o merged.pdf
Every response carries X-Filewash-Meta (operation result) and X-Filewash-Quota-Remaining.
Tools
| Tool | Category | What it does |
|---|---|---|
pdf_merge |
Merge PDFs into one | |
pdf_split |
Extract specific pages | |
pdf_rotate |
Rotate pages by 90° | |
pdf_strip_metadata |
privacy | Remove author/title/producer/dates |
image_compress |
image | Lossy re-encode at a target quality |
image_convert |
image | jpeg ↔ png ↔ webp ↔ avif |
image_resize |
image | Resize (never upscales) |
image_strip_metadata |
privacy | Strip EXIF/GPS/ICC/XMP |
image_remove_background |
image | Remove background → transparent PNG (local AI model, no upload) |
image_watermark |
image | Tile a text watermark |
qr_generate |
generate | QR code PNG from text/URL |
Pricing (planned)
| Plan | Price | Quota | Retention |
|---|---|---|---|
| Free | $0 | 100 ops/mo | in-memory |
| Pro | ~$19/mo | 10,000 ops/mo | in-memory |
| Business | ~$99/mo | unlimited | zero-retention guarantee + audit log + BAA |
Run locally
npm install
npm run test:engine # 10 tools, end-to-end, no browser
npm run mcp # stdio MCP server
npm run rest # REST API on :8787 (try key "demo")
Privacy
No file is written to disk by the REST API; the MCP server writes output only to the path you pass. No file contents are logged. The Business tier adds a contractual zero-retention guarantee and audit logging.
Recommended MCP Servers
How it compares
Privacy-oriented file-ops MCP, not a browser automation or generic cloud storage integration.
FAQ
Who is Filewash for?
Developers and developers using Claude Code or similar agents who need PDF, image, and metadata utilities without sending files to random external services.
When should I use Filewash?
Use it while building agent workflows or preparing launch content when you must strip EXIF/metadata, tweak PDFs or images, or remove backgrounds as part of your pipeline.
How do I add Filewash to my agent?
Add the stdio MCP entry for @fixpixel/filewash-api (Node), install via npm registry, and point your client at the published server configuration from the filewash-api GitHub repo.