Compatible with every major AI agent and IDE
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_documentswith 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 withdownload_document, or get instant visual context withpreview_documentandthumb_document. - Metadata Management — Organize your library by creating and updating tags, correspondents, and document types using dedicated tools like
create_tagorupdate_correspondent. - Deep Inspection — Fetch complete OCR text and metadata for any specific file using
get_documentto 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 a new correspondent
Create a new document type
Create a new saved view
Create a new tag
Delete a correspondent
Delete a document
Delete a document type
Delete a saved view
Delete a tag
Download the actual document file
Retrieve correspondent details
Retrieve details of a specific document
Retrieve document type details
Retrieve tag details
List all correspondents
List all document types
Supports filtering and searching via query parameters. List all documents in Paperless-ngx
List all saved views
List all tags
Get a preview of the document
Get the document thumbnail
Update a correspondent
Update document metadata
Update a document type
Update a tag
Upload a new document
Why Vercel AI SDK?
The Vercel AI SDK gives every Paperless-ngx tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 26 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.
- —
TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box
- —
Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same Paperless-ngx integration everywhere
- —
Built-in streaming UI primitives let you display Paperless-ngx tool results progressively in React, Svelte, or Vue components
- —
Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency
Paperless-ngx in Vercel AI SDK
Paperless-ngx and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Paperless-ngx to Vercel AI SDK 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.
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 |
Why teams choose Vinkius for Paperless-ngx in Vercel AI SDK
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 Vercel AI SDK 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.

* 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
How Vinkius secures
Paperless-ngx for Vercel AI SDK
Every tool call from Vercel AI SDK to the Paperless-ngx MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
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 the Vercel AI SDK connect to MCP servers?
Import createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.
Can I use MCP tools in Edge Functions?
Yes. The AI SDK is fully edge-compatible. MCP connections work on Vercel Edge Functions, Cloudflare Workers, and similar runtimes.
Does it support streaming tool results?
Yes. The SDK provides streaming primitives like useChat and streamText that handle tool calls and display results progressively in the UI.
createMCPClient is not a function
Install: npm install @ai-sdk/mcp
Explore More MCP Servers
View all →
Shimo Docs
10 toolsCollaborative office suite and document management platform — manage Word, Excel, and PPT via AI.

BCB Economia — PIB, Dívida, Reservas, PIX e SGS
7 toolsBrazilian economic indicators: monthly GDP proxy (IBC-Br), public debt/GDP ratio, international reserves, trade balance, unemployment rate (PNAD), PIX payment statistics, and universal access to 20,000+ BCB time series via SGS codes.

Apify Alternative
10 toolsManage your cloud automation — audit actors, tasks, and datasets via AI.

Corsizio
10 toolsEquip your AI agent to manage event registrations, attendees, and payments through the Corsizio API.
