Paperless-ngx MCP Server: Give AI Agents Access to Your Documents, Tags, and OCR Content

Why Give AI Access to Paperless-ngx?

Paperless-ngx is the self-hosted document management system that scans, OCRs, tags, and organizes your paper documents. It indexes every document with full-text search, assigns correspondents and document types, and makes your entire filing cabinet searchable.

But when you're coding in Claude or Cursor, your AI assistant can't see your Paperless instance. It can't search for a specific invoice, check if a document was processed, or pull text from a scanned receipt. You end up switching to the Paperless web UI constantly.

With DataFaucet, you browse your Paperless-ngx dashboard once and it captures the API calls as MCP tools. Now your AI coding assistant can search documents, read OCR content, and check processing status directly.

What AI Agents Can Do With Paperless-ngx Access

Once DataFaucet creates an MCP server from your Paperless-ngx session, AI agents can:

• Search documents by content, title, date range, correspondent, or tag
• Read OCR text from any scanned document without downloading the file
• List tags and correspondents with document counts
• Check processing queue for new documents being consumed
• View document metadata including added date, modified date, and archive serial number
• Browse document types and their classification rules
• Check storage paths and document organization structure

Setting Up Paperless-ngx as an MCP Server with DataFaucet

1. Open your Paperless-ngx web interface and navigate through documents, tags, correspondents, and settings
2. DataFaucet captures the API calls your browser makes to Paperless-ngx's REST API
3. Click "Create MCP Server" and DataFaucet generates structured tools from those endpoints
4. Add the MCP server URL to your AI client (Claude, Cursor, Windsurf)
5. Your AI can now query Paperless-ngx data in real-time

The entire process takes about two minutes. Works with any self-hosted Paperless-ngx instance.

Example Queries Your AI Can Answer

After connecting, try asking your AI:

• "Find all invoices from Amazon in the last 3 months"
• "What documents are waiting in the consumption queue?"
• "Pull the text from the most recent tax document"
• "How many documents are tagged as 'receipts'?"
• "Which correspondents have the most documents?"
• "Was the insurance renewal letter scanned yet?"

Your AI can answer these instantly because it has real-time access to your Paperless-ngx API through MCP tools.

DataFaucet vs Paperless-ngx REST API

Self-Hosted Paperless-ngx Works Perfectly

Since DataFaucet captures API calls from your browser, it works with any Paperless-ngx instance on your network. Your AI assistant gets access to the same data you see in the web UI, whether Paperless runs on Docker, bare metal, or a NAS.

Use Cases

• Document lookup while coding: Search for config docs or contracts without leaving your editor
• Automation scripting: AI reads document metadata to help you write tagging rules
• Audit preparation: AI searches across all documents for specific content or date ranges
• Processing verification: Check if recently scanned documents were consumed and tagged
• Data extraction: AI reads OCR text from receipts or invoices for your scripts

Get Started

DataFaucet turns your Paperless-ngx web interface into structured MCP tools in under two minutes. No API tokens to create, no custom scripts, no configuration changes.

Create your Paperless-ngx MCP server and give your AI coding assistant full visibility into your document archive.