This MCP server provides integration between Claude AI and your Paperless-NGX document management system, allowing you to search, create, and manage documents, tags, correspondents, and document types through natural language commands.
The easiest way to install the Paperless-NGX MCP server is with Smithery:
npx -y @smithery/cli install @nloui/paperless-mcp --client claude
npm install -g paperless-mcp
For VSCode extension:
Edit ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
:
{
"mcpServers": {
"paperless": {
"command": "npx",
"args": ["paperless-mcp", "http://your-paperless-instance:8000", "your-api-token"]
}
}
}
For Claude desktop app:
Edit ~/Library/Application Support/Claude/claude_desktop_config.json
:
{
"mcpServers": {
"paperless": {
"command": "npx",
"args": ["paperless-mcp", "http://your-paperless-instance:8000", "your-api-token"]
}
}
}
Replace the placeholders in your MCP config with your actual Paperless-NGX URL and API token.
Once configured, you can ask Claude to help manage your Paperless-NGX documents using natural language. Here are some example prompts:
To list all documents (paginated):
list_documents({
page: 1,
page_size: 25
})
To get a specific document by ID:
get_document({
id: 123
})
To search documents:
search_documents({
query: "invoice 2024"
})
To download a document file:
download_document({
id: 123,
original: false // set to true for the original file instead of archived version
})
To add a new document:
post_document({
file: "base64_encoded_content",
filename: "invoice.pdf",
title: "January Invoice",
created: "2024-01-19",
correspondent: 1,
document_type: 2,
tags: [1, 3],
archive_serial_number: "2024-001"
})
The system supports powerful bulk operations on multiple documents:
// Add a tag to multiple documents
bulk_edit_documents({
documents: [1, 2, 3],
method: "add_tag",
tag: 5
})
// Merge documents
bulk_edit_documents({
documents: [6, 7, 8],
method: "merge",
metadata_document_id: 6,
delete_originals: true
})
// Split document into parts
bulk_edit_documents({
documents: [9],
method: "split",
pages: "[1-2,3-4,5]"
})
To list all tags:
list_tags()
To create a new tag:
create_tag({
name: "Invoice",
color: "#ff0000",
match: "invoice",
matching_algorithm: "fuzzy"
})
To list all correspondents:
list_correspondents()
To create a new correspondent:
create_correspondent({
name: "ACME Corp",
match: "ACME",
matching_algorithm: "fuzzy"
})
To list all document types:
list_document_types()
To create a new document type:
create_document_type({
name: "Invoice",
match: "invoice total amount due",
matching_algorithm: "any"
})
If you encounter issues, check that:
The server will provide error messages if there are problems with connectivity, authentication, or parameter validation.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.