Paperless MCP Server

Paperless mcp mcp server lets Claude, Cursor and other MCP clients work with Paperless MCP directly. Model Context Protocol (MCP) server for interacting with Paperless-NGX document management system. Enables AI assistants to manage documents, tags, correspondents, and document types through the Paperless-NGX API.

What Paperless MCP does

An MCP (Model Context Protocol) server for interacting with a Paperless-NGX API server. This server provides tools for managing documents, tags, correspondents, and document types in your Paperless-NGX instance.

Tools it exposes

Once connected, the assistant can call these 14 tools directly:

• Scenario — --no-auth off (default)
• Installation — // STDIO mode (recommended for local or CLI use) json "paperless": { "command": "npx", "args": [ "-y", "@baruchiro/paperless-mcp@latest", ], "env": {
• list_documents — Get a paginated list of documents with simple filters. Use this for straightforward listing tasks. For full-text queries, structured custom field filtering, or
• query_documents — Canonical document query tool. Supports full-text querying, simple Paperless search, custom field filters, and documented /api/documents/ Paperless query
• get_document — The get_document tool exposed by this server
• search_documents — Deprecated compatibility wrapper for full-text search. Prefer query_documents({ query: ... }) for new integrations
• download_document — Parameters: - id: Document ID - original (optional): If true, downloads original file instead of archived version
• get_document_thumbnail — Get a document thumbnail (image preview) by ID. Returns the thumbnail as a base64-encoded WebP image resource
• bulk_edit_documents — Parameters: - documents: Array of document IDs - method: One of: - set_correspondent: Set correspondent for documents - set_document_type: Set document type
• post_document — 1. Base64 mode (traditional): Provide file (base64-encoded content) + filename 2. Filesystem mode (efficient): Provide file_path (absolute path on
• list_document_notes — The list_document_notes tool exposed by this server
• create_document_note — Add a note to a document. Returns the document's full list of notes
• delete_document_note — ⚠️ Delete a single note from a document by its note ID. This operation is irreversible
• list_tags — The list_tags tool exposed by this server

Installing the paperless mcp mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Configuration

Before the server will start you need to supply 4 environment variables: PAPERLESS_URL, PAPERLESS_API_KEY, PAPERLESS_PUBLIC_URL, PAPERLESS_TOKEN. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

Productivity servers pay off through capture: the tasks and notes that never get filed are the ones where opening the app is more friction than the thought is worth. Paperless MCP sits in that group, and the shape of its toolset — Scenario, Installation, list_documents among others — tells you what it is really for. Worth comparing against the other productivity servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

• This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
• It will not start until its required credentials are present, so set those before wondering why the tools never appear.
• With 14 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use Paperless MCP.
• Maintained by baruchiro, written in TypeScript.
• MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the paperless mcp mcp server actually does with your data.
• Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.