PaperlessMCP

Stop manually organizing your documents. Let AI do it.

You've got a Paperless-ngx instance. You've got hundreds (thousands?) of documents. You know you should tag them, set correspondents, organize them properly. But who has time for that?

PaperlessMCP connects your Paperless-ngx to any MCP-compatible AI. Now instead of clicking through the UI, you just ask:

"Find all my tax documents from 2023"

"Tag these 50 invoices as 'Business Expense' and set the correspondent to 'Acme Corp'"

"Upload this receipt and figure out what it is"

"What documents am I missing from my insurance folder?"

It's Paperless-ngx on LLM steroids. An interface designed specifically for AI to manage your documents while you do literally anything else.

---

What Can AI Do With Your Paperless?

Everything. Full CRUD on every entity type:

You Say	AI Does
"Find receipts from Amazon over $100"	Searches documents with filters
"Tag all 2024 invoices as 'Tax Year 2024'"	Bulk updates dozens of docs at once
"Upload this PDF and file it appropriately"	Uploads, auto-tags, sets correspondent
"Delete all documents tagged 'Junk'"	Removes with confirmation (dry-run by default)
"Create a tag for medical records, make it red"	Creates tag with color
"Who sends me the most documents?"	Lists correspondents by document count
"Set up a storage path for legal documents"	Creates organized folder structure

43 tools covering:

• Documents — search, upload, download, update, delete, bulk operations, OCR reprocessing
• Tags — full CRUD with colors and matching rules
• Correspondents — track who sends you stuff
• Document Types — classify invoices, receipts, contracts, whatever
• Storage Paths — organize files with smart templates
• Custom Fields — add your own metadata (dates, amounts, URLs, etc.)

All destructive operations require explicit confirmation and default to dry-run mode. AI can't nuke your archive by accident.

---

Is PaperlessMCP Right For You?

Yes, if:

• You run Paperless-ngx (self-hosted or cloud)
• You use any AI assistant that speaks MCP (Claude, or anything else supporting the protocol)
• You have a backlog of untagged documents and feel guilty about it
• You'd rather say "organize this" than click 47 buttons
• You want to query your documents in plain English
• You think computers should work for you, not the other way around

No, if:

• You don't use Paperless-ngx (this isn't a general document tool)
• You enjoy manually tagging documents (weirdo, but respect)
• You don't trust AI with your files (fair, but you can dry-run everything first)

The sweet spot: You've got Paperless running, you've got an MCP-compatible AI, and you want them to be friends.

---

Getting Started

You'll Need

1. A Paperless-ngx instance with an API token (Settings → Django Admin → Tokens → Create one for your user)

2. An MCP-compatible AI (Claude Desktop, or anything speaking the protocol)

Option 1: Docker (Recommended)

The fastest path from zero to talking to your documents.

docker run -d \
  --name paperless-mcp \
  --restart unless-stopped \
  -e PAPERLESS_BASE_URL=https://your-paperless.example.com \
  -e PAPERLESS_API_TOKEN=your-token-here \
  -p 5000:5000 \
  ghcr.io/barryw/paperlessmcp:vX.Y.Z

Grab the version from the badge above. We don't use latest because you deserve reproducible deployments.

Connect your MCP client to http://localhost:5000/mcp and start talking to your documents.

Option 2: Claude Desktop

Add to your config file:

OS	Path
macOS	~/Library/Application Support/Claude/claude_desktop_config.json
Windows	%APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "paperless": {
      "command": "dotnet",
      "args": ["run", "--project", "/path/to/PaperlessMCP/PaperlessMCP", "--", "--stdio"],
      "env": {
        "PAPERLESS_BASE_URL": "https://your-paperless.example.com",
        "PAPERLESS_API_TOKEN": "your-token-here"
      }
    }
  }
}

Restart Claude Desktop. Look for the tools icon — Paperless should be there.

Option 3: Claude Code

One command if you're already running the server somewhere:

# Connect to a running HTTP/SSE server
claude mcp add --transport sse paperless http://localhost:5000/mcp

Or run from source with stdio:

claude mcp add --transport stdio paperless \
  -e PAPERLESS_BASE_URL=https://your-paperless.example.com \
  -e PAPERLESS_API_TOKEN=your-token-here \
  -- dotnet run --project /path/to/PaperlessMCP/PaperlessMCP -- --stdio

Verify it's there:

claude mcp list

Option 4: Kubernetes

For the homelabbers running k8s. We include ready-to-use manifests with Kustomize support.

# Clone and customize
git clone https://github.com/barryw/PaperlessMCP.git
cd PaperlessMCP/k8s

# Create your secrets
kubectl create secret generic paperless-mcp \
  --from-literal=PAPERLESS_BASE_URL=https://your-paperless.example.com

kubectl create secret generic paperless-token \
  --from-literal=token=your-api-token-here

# Deploy (edit the image tag first)
kubectl apply -k .

See the manifests

Includes: Deployment, Service, Ingress, Kustomization. Tweak to taste.

Option 5: From Source

For contributors and tinkerers:

git clone https://github.com/barryw/PaperlessMCP.git
cd PaperlessMCP
dotnet run --project PaperlessMCP             # HTTP/SSE on :5000
dotnet run --project PaperlessMCP -- --stdio  # stdio mode

Requires .NET 10 SDK.

---

The Full Toolbox

43 tools, organized by what they touch. Every entity supports full CRUD.

Documents — the main event

Tool	What it does
paperless_documents_search	Find documents with full-text search and filters
paperless_documents_get	Get a document by ID with all metadata
paperless_documents_upload	Upload a document (base64)
paperless_documents_upload_from_path	Upload from a file path
paperless_documents_update	Update title, tags, correspondent, etc.
paperless_documents_delete	Delete a document (requires confirmation)
paperless_documents_bulk_update	Update multiple documents at once
paperless_documents_download	Get download URL for original file
paperless_documents_preview	Get preview URL
paperless_documents_thumbnail	Get thumbnail URL
paperless_documents_reprocess	Re-run OCR on a document

Tags — organize everything

Tool	What it does
paperless_tags_list	List all tags
paperless_tags_get	Get a tag by ID
paperless_tags_create	Create a tag with optional color and matching rules
paperless_tags_update	Update a tag
paperless_tags_delete	Delete a tag
paperless_tags_bulk_delete	Delete multiple tags

Correspondents — who sends you stuff

Tool	What it does
paperless_correspondents_list	List all correspondents
paperless_correspondents_get	Get a correspondent by ID
paperless_correspondents_create	Create with optional matching rules
paperless_correspondents_update	Update a correspondent
paperless_correspondents_delete	Delete a correspondent
paperless_correspondents_bulk_delete	Delete multiple correspondents

Document Types — invoices, receipts, contracts...

Tool	What it does
paperless_document_types_list	List all document types
paperless_document_types_get	Get a document type by ID
paperless_document_types_create	Create with optional matching rules
paperless_document_types_update	Update a document type
paperless_document_types_delete	Delete a document type
paperless_document_types_bulk_delete	Delete multiple document types

Storage Paths — where things live

Tool	What it does
paperless_storage_paths_list	List all storage paths
paperless_storage_paths_get	Get a storage path by ID
paperless_storage_paths_create	Create with path template
paperless_storage_paths_update	Update a storage path
paperless_storage_paths_delete	Delete a storage path
paperless_storage_paths_bulk_delete	Delete multiple storage paths

Custom Fields — your own metadata

Tool	What it does
paperless_custom_fields_list	List all custom field definitions
paperless_custom_fields_get	Get a custom field by ID
paperless_custom_fields_create	Create a field (string, date, number, monetary, etc.)
paperless_custom_fields_update	Update a field definition
paperless_custom_fields_delete	Delete a field
paperless_custom_fields_assign	Assign a field value to a document

Health — is it alive?

Tool	What it does
paperless_ping	Check connectivity and auth
paperless_capabilities	List supported features

---

Configuration

Environment variables. That's it. No config files to manage.

Variable	Required	Default	Description
PAPERLESS_BASE_URL	Yes	—	Your Paperless-ngx URL
PAPERLESS_API_TOKEN	Yes	—	API token for authentication
MCP_PORT		5000	Port for HTTP/SSE mode
MAX_PAGE_SIZE		100	Max items per paginated request

Aliases supported: PAPERLESS_URL and PAPERLESS_TOKEN also work if that's your style.

---

Support the Project

If PaperlessMCP saves you time, consider supporting development:

Every bit helps keep the lights on and the commits flowing.

---

Contributing

Yes please. We use trunk-based development with conventional commits.

git clone https://github.com/barryw/PaperlessMCP.git
cd PaperlessMCP
dotnet build
dotnet test

The rules:

• Conventional commits (feat:, fix:, docs:, etc.) — versions bump automatically
• Tests pass or it doesn't merge
• Destructive operations need confirm=true and dry-run by default

See CONTRIBUTING.md for the full rundown.

---

License

MIT — do whatever you want, just don't blame me.

---

Acknowledgments

• Paperless-ngx — the document system that makes this worth building
• Model Context Protocol — the glue between AI and everything else
• Everyone who's ever felt guilty about their untagged documents