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:

43 tools covering:

• Documents — search, upload, download, update, delete, bulk operations, OCR reprocessing
• Tags — full CRUD with colors, matching rules, and hierarchical parents
• 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. Bulk operations default to dry-run mode, so 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; destructive operations require confirmation, and bulk operations default to dry-run)

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. The release pipeline also publishes latest, but pinning a versioned tag gives you a reproducible deployment.

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

Option 2: Claude Desktop

Add to your config file:

{
  "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 Streamable HTTP server
claude mcp add --transport http 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: LiteLLM Proxy

LiteLLM can register PaperlessMCP as a Streamable HTTP MCP server in config.yaml.

Start PaperlessMCP first using Docker, Kubernetes, or source, then add it to LiteLLM:

mcp_servers:
  paperless:
    url: "http://paperless-mcp:5000/mcp"
    transport: "http"
    description: "Paperless-ngx document management"

Use a URL that the LiteLLM process can reach. In Docker Compose, set the host to the PaperlessMCP service name from that Compose file, such as paperless-mcp. If LiteLLM runs directly on the host and PaperlessMCP publishes port 5000, use http://127.0.0.1:5000/mcp.

Set transport: "http" explicitly for PaperlessMCP's /mcp endpoint. LiteLLM's MCP config defaults to sse, which is the wrong transport for this endpoint.

PAPERLESS_API_TOKEN belongs on the PaperlessMCP service; it is the token PaperlessMCP uses when calling Paperless-ngx. PaperlessMCP does not require an inbound token on /mcp unless you put a separate auth layer, such as a reverse proxy, in front of it.

For LiteLLM database-backed MCP storage, enable database storage in LiteLLM:

general_settings:
  store_model_in_db: true

For static configuration, keep the server under the top-level mcp_servers key.

Option 5: 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

# Customize the checked-in manifests:
# - Set PAPERLESS_BASE_URL in secret.yaml.
# - Pin a versioned image tag in deployment.yaml.
# - The image is public, so remove imagePullSecrets unless your cluster
#   provides the referenced ghcr-secret.

# Create the API token secret (it is not managed by kustomization.yaml)
kubectl create secret generic paperless-token \
  --from-literal=token=your-api-token-here

# Deploy
kubectl apply -k .

See the manifests

Includes: Deployment, Service, Ingress, base-URL Secret, and Kustomization. Tweak to taste.

Option 6: From Source

For contributors and tinkerers:

git clone https://github.com/barryw/PaperlessMCP.git
cd PaperlessMCP
dotnet run --project PaperlessMCP             # Streamable HTTP 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.

Configuration

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

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

LocalAI Compatibility

Streamable HTTP clients are expected to send Accept: application/json, text/event-stream on /mcp POST requests. Some clients cannot configure that header. Set MCP_RELAX_ACCEPT_HEADER=true to have PaperlessMCP normalize missing or incomplete Accept headers before the MCP SDK handles the request.

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; bulk operations default to dry-run

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