Pydantic AISDK

Paperless-ngx MCP Server

Bring Digital Archive
to Pydantic AI

Name: Paperless-ngx MCP Server
Price: 29 USD
Availability: InStock
Rating: 4.9 (1 reviews)
Author: Vinkius

Learn how to connect Paperless-ngx to Pydantic AI and start using 26 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.

GDPR Free for Subscribers

Create CorrespondentCreate Document TypeCreate Saved ViewCreate TagDelete CorrespondentDelete DocumentDelete Document TypeDelete Saved ViewDelete TagDownload DocumentGet CorrespondentGet DocumentGet Document TypeGet TagList CorrespondentsList Document TypesList DocumentsList Saved ViewsList TagsPreview DocumentThumb DocumentUpdate CorrespondentUpdate DocumentUpdate Document TypeUpdate TagUpload Document

Unlock for AI Agents

Ask AI about this MCP Server ChatGPT Claude Perplexity

Compatible with every major AI agent and IDE

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

What is the Paperless-ngx MCP Server?

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

Subscribe to this server
Provide your Paperless-ngx API URL and Personal API Token
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.

Built-in capabilities (26)

create_correspondent

Create a new correspondent

create_document_type

Create a new document type

create_saved_view

Create a new saved view

create_tag

Create a new tag

delete_correspondent

Delete a correspondent

delete_document

Delete a document

delete_document_type

Delete a document type

delete_saved_view

Delete a saved view

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

list_saved_views

List all saved views

list_tags

List all tags

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

Why Pydantic AI?

Pydantic AI validates every Paperless-ngx tool response against typed schemas, catching data inconsistencies at build time. Connect 26 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

—
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
—
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Paperless-ngx integration code
—
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
—
Dependency injection system cleanly separates your Paperless-ngx connection logic from agent behavior for testable, maintainable code

See it in action

Paperless-ngx in Pydantic AI

AI Agent→Vinkius

High Security·Kill Switch·Plug and Play

Why Vinkius

Paperless-ngx and 4,000+ other MCP servers. One platform. One governance layer.

Teams that connect Paperless-ngx to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.

4,000+MCP Servers ready

<40msCold start

60%Token savings

	Raw MCP	Vinkius
Server catalog	Find and host yourself	4,000+ managed
Infrastructure	Self-hosted	Sandboxed V8 isolates
Credential handling	Plaintext in config	Vault + runtime injection
Data loss prevention	None	Configurable DLP policies
Kill switch	None	Global instant shutdown
Financial circuit breakers	None	Per-server limits + alerts
Audit trail	None	Ed25519 signed logs
SIEM log streaming	None	Splunk, Datadog, Webhook
Honeytokens	None	Canary alerts on leak
Custom domains	Not applicable	DNS challenge verified
GDPR compliance	Manual effort	Automated purge + export

Unlock for AI Agents View step-by-step setup guide for Pydantic AI →

Enterprise Security

Why teams choose Vinkius for Paperless-ngx in Pydantic AI

The Paperless-ngx MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 26 tools execute in hardened sandboxes optimized for native MCP execution.

Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

Unlock for AI Agents View full Paperless-ngx details →

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

The Vinkius Advantage

How Vinkius secures
Paperless-ngx for Pydantic AI

Every tool call from Pydantic AI to the Paperless-ngx MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.

< 40msCold start

Ed25519Signed audit chain

60%Token savings

FAQ

Frequently asked questions

Can I search for documents using specific tags or date ranges?

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.

Is it possible to see a preview of a document without downloading the whole file?

Absolutely. Use the preview_document or thumb_document tools to get visual representations of the document content directly through the agent.

Can I create new organization categories like tags or correspondents via AI?

Yes, you have full management capabilities. You can use create_tag, create_correspondent, and create_document_type to organize your archive on the fly.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Paperless-ngx MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.