Paperless-ngx

Paperless-ngx MCP Connector for Claude

A+

Manage your digital archive via Paperless-ngx — search documents, upload files, manage tags, and organize correspondents directly from any AI agent.

26 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Paperless-ngx instance to any AI agent and transform your document archive into a searchable, conversational knowledge base.

What you can do

  • Document Discovery — Use list_documents with full-text search or filter by tags and dates to find exactly what you need in seconds.
  • File Operations — Upload new documents with upload_document, download originals with download_document, or get instant visual context with preview_document and thumb_document.
  • Metadata Management — Organize your library by creating and updating tags, correspondents, and document types using dedicated tools like create_tag or update_correspondent.
  • Deep Inspection — Fetch complete OCR text and metadata for any specific file using get_document to help your AI analyze contents.
  • Saved Views — Access your predefined filters and organizational structures with list_saved_views.

How it works

  1. Subscribe to this server
  2. Provide your Paperless-ngx API URL and Personal API Token
  3. Start chatting with your documents in Claude, Cursor, or any MCP-compatible client

No more manual searching through folders. Your AI acts as a digital librarian that knows every word in your archive.

Who is this for?

  • Home Office Users — instantly find utility bills, tax records, or manuals without digging through physical or digital piles.
  • Legal & Admin Teams — query specific correspondents or document types to build reports or verify information quickly.
  • Researchers — manage large collections of PDFs and papers with automated tagging and content retrieval.
digital-archiveocrfull-text-searchfile-managementdocument-indexingopen-source

26 tools expose this connector's capabilities to your AI agent.

list_tags

List all tags

delete_tag

Delete a tag

download_document

Download the actual document file

get_correspondent

Retrieve correspondent details

get_document

Retrieve details of a specific document

get_document_type

Retrieve document type details

get_tag

Retrieve tag details

list_correspondents

List all correspondents

list_document_types

List all document types

list_documents

Supports filtering and searching via query parameters. List all documents in Paperless-ngx

preview_document

Get a preview of the document

thumb_document

Get the document thumbnail

update_correspondent

Update a correspondent

update_document

Update document metadata

update_document_type

Update a document type

update_tag

Update a tag

upload_document

Upload a new document

create_tag

Create a new tag

create_correspondent

Create a new correspondent

create_document_type

Create a new document type

create_saved_view

Create a new saved view

list_saved_views

List all saved views

delete_correspondent

Delete a correspondent

delete_document

Delete a document

delete_document_type

Delete a document type

delete_saved_view

Delete a saved view

See how to talk to your AI agent using Paperless-ngx.

Search for all documents related to 'Electricity Bill' from 2023.

I've searched your archive using `list_documents`. I found 3 documents: 'Jan 2023 Electricity' (ID: 101), 'Feb 2023 Electricity' (ID: 105), and 'March 2023 Electricity' (ID: 110). Would you like to see the details of one of them?

Upload a new document titled 'Contract 2024' with tag ID 12.

Processing the upload... I've successfully used `upload_document` to add 'Contract 2024'. It has been assigned ID 250 and is now being processed by Paperless-ngx for OCR.

Get the full content and a preview of document ID 42.

I've retrieved the data for document 42 using `get_document` and `preview_document`. The document is a 'Lease Agreement'. The OCR text mentions a monthly rent of $1,200. I've also generated a preview link for you.

Yes. The `list_documents` tool allows you to filter by `tags__id__in` and `created__date__gte`. You can also perform a full-text search using the `query` parameter.

Related Connectors