mcpField
F
filewash

filewash

Local
github.com/cassilupMedia & Design0Updated 20w ago

About filewash

filewash provides file-processing tools for agents and applications that should not send files to third parties. Its MCP server, REST API, and npm SDK support PDF and image operations, including metadata removal and background removal; files are processed in memory by default without being stored or logged.

Key features

  1. 01PDF merge, split, and rotation
  2. 02Image compression, conversion, and resizing
  3. 03PDF and image metadata removal
  4. 04Background removal to transparent PNG
  5. 05QR code generation
  6. 06In-memory processing by default

Use cases

  1. 01Remove location metadata from photos
  2. 02Prepare PDFs by merging or extracting pages
  3. 03Convert or resize images for an application
  4. 04Remove image backgrounds without uploading files

MCP support

The MCP server exposes 11 tools for PDF and image operations, metadata scrubbing, background removal, watermarking, and QR generation. The server writes output only to the path supplied.

Configuration

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

mcp.json · Universal config
{
"mcpServers": {
"cassilup-filewash": {
"command": "npx",
"args": [
"-y",
"@fixpixel/filewash-api"
]
}
}
}
Run commandnpx -y @fixpixel/filewash-api

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@fixpixel/filewash-api0.1.0

Tools

11

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
inputsarrayYesPaths to the input files (or data: URLs / base64).
outputPathstringNoWhere to write the result. Defaults to a temp file; the path is returned.

Details

From the project README

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 '[email protected]' -o clean.jpg

# merge PDFs
curl -X POST https://api.filewash.app/v1/tools/pdf_merge \
  -H "Authorization: Bearer $FILEWASH_KEY" \
  -F '[email protected]' -F '[email protected]' -o merged.pdf

Every response carries X-Filewash-Meta (operation result) and X-Filewash-Quota-Remaining.

Tools

ToolCategoryWhat it does
pdf_mergepdfMerge PDFs into one
pdf_splitpdfExtract specific pages
pdf_rotatepdfRotate pages by 90°
pdf_strip_metadataprivacyRemove author/title/producer/dates
image_compressimageLossy re-encode at a target quality
image_convertimagejpeg ↔ png ↔ webp ↔ avif
image_resizeimageResize (never upscales)
image_strip_metadataprivacyStrip EXIF/GPS/ICC/XMP
image_remove_backgroundimageRemove background → transparent PNG (local AI model, no upload)
image_watermarkimageTile a text watermark
qr_generategenerateQR code PNG from text/URL

Pricing (planned)

PlanPriceQuotaRetention
Free$0100 ops/moin-memory
Pro~$19/mo10,000 ops/moin-memory
Business~$99/mounlimitedzero-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.

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.