paperless-ngx-mcp 0.1.0

Paperless-ngx API + MCP Server + A2A Server

Paperless-ngx MCP

CLI or API | MCP | Agent

Version: 0.1.0

Documentation — Installation, deployment, usage across the API, CLI, and MCP interfaces, the integrated A2A agent server, and guidance for provisioning the backing platform are maintained in the official documentation.

---

Table of Contents

• Overview
• Key Features
• Available MCP Tools
• Installation
• Usage
• MCP
• Documentation

---

Overview

Paperless-ngx MCP MCP Server + A2A Agent

Paperless-ngx API + MCP Server + A2A Server

This repository is actively maintained - Contributions are welcome!

Key Features

• Action-routed MCP tools — each domain is exposed as a single MCP tool that routes to many underlying operations via an action argument, keeping the tool surface small.
• Three interfaces, one package — use it as a Python API client, an MCP server (stdio / streamable-http / sse), or a Pydantic-AI A2A agent.
• agent-utilities native — built on the shared framework (auth, action router, telemetry, governance) for fleet consistency.
• Per-tool toggles — enable or disable each tool domain with environment switches.
• Enterprise-ready — OTEL/Langfuse telemetry and optional Eunomia access governance.

Available MCP Tools

Each tool is action-routed: pass an action and a JSON params_json payload. Tool domains can be toggled on or off with the listed environment variable. The table below is auto-generated from the live server by the mcp-readme-table pre-commit hook (python -m agent_utilities.mcp.readme_tools) — do not edit it by hand.

MCP Tool	Toggle Env Var	Description
document_operations	DOCUMENTSTOOL	Manage Paperless-ngx documents, correspondents, tags, document types,
system_operations	SYSTEMTOOL	Run Paperless-ngx full-text search, inspect background/consumption tasks,

2 action-routed tools (default MCP_TOOL_MODE=condensed). Each is enabled unless its toggle is set false; set MCP_TOOL_MODE=verbose (or both) for the 1:1 per-operation surface. Auto-generated — do not edit.

Installation

Install with uvx (no install — run on demand)

uvx --from paperless-ngx-mcp paperless-ngx-mcp      # MCP server
uvx --from paperless-ngx-mcp paperless-ngx-agent    # A2A agent server

Install with pip

python -m pip install paperless-ngx-mcp            # core (API client)
python -m pip install "paperless-ngx-mcp[all]"     # + MCP server + A2A agent + telemetry

Console scripts

After installation the following entry points are available on your PATH:

Command	Description
paperless-ngx-mcp	Launch the MCP server
paperless-ngx-agent	Launch the A2A agent server

Usage

As a Python API client

from paperless_ngx_mcp.auth import get_client

client = get_client()
status = client.get_system_status()
print(status)

As an MCP server (CLI)

# Local stdio (for IDEs)
paperless-ngx-mcp

# Networked streamable-http
paperless-ngx-mcp --transport streamable-http --host 0.0.0.0 --port 8000

Calling an MCP tool

Tools are action-routed — pass an action plus a JSON params_json string:

{
  "tool": "system_operations",
  "arguments": {
    "action": "status",
    "params_json": "{}"
  }
}

MCP

Using as an MCP Server

The MCP Server can be run in stdio (local), streamable-http (networked), or sse mode.

Environment Variables

• PAPERLESS_URL: The URL of the target service.
• PAPERLESS_TOKEN: The API token or access token.

stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)

{
  "mcpServers": {
    "paperless-ngx-mcp": {
      "command": "uvx",
      "args": ["--from", "paperless-ngx-mcp", "paperless-ngx-mcp"],
      "env": {
        "PAPERLESS_URL": "https://service.example.com",
        "PAPERLESS_TOKEN": "your_token"
      }
    }
  }
}

Streamable-HTTP Transport (networked / production)

{
  "mcpServers": {
    "paperless-ngx-mcp": {
      "command": "uvx",
      "args": ["--from", "paperless-ngx-mcp", "paperless-ngx-mcp", "--transport", "streamable-http", "--port", "8000"],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000",
        "PAPERLESS_URL": "https://service.example.com",
        "PAPERLESS_TOKEN": "your_token"
      }
    }
  }
}

Additional Deployment Options

paperless-ngx-mcp can also run as a local container (Docker / Podman / uv) or be consumed from a remote deployment. The Deployment guide has full, copy-paste mcp_config.json for all four transports — stdio, streamable-http, local container / uv, and remote URL:

• Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run, or point at a local streamable-http container by url.
• Remote URL — connect to a server deployed behind Caddy at http://paperless-ngx-mcp.arpa/mcp using the "url" key.

Install Python Package

python -m pip install paperless-ngx-mcp

Documentation

Full documentation is published to the GitHub Pages site and mirrored under docs/:

• Documentation site
• Overview
• Installation
• Usage
• Deployment
• Platform
• Concept Registry