What is PaperlessMCP CLAUDE.md?

Project instructions for PaperlessMCP, a server that connects Paperless-ngx document management to AI assistants through MCP, a standard for exposing tools to assistants. They describe building, testing, required settings, and local stdio or HTTP operation.

Use them when building, testing, configuring, or running PaperlessMCP locally or connecting it to an AI assistant.

They give developers the commands and configuration needed to run the server correctly and keep changes aligned with its architecture.

How barryw/PaperlessMCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to barryw/PaperlessMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/barryw/PaperlessMCP/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/barryw/PaperlessMCP

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/barryw/paperlessmcp/claude-md/github.svg)](https://agentmods.dev/instructions/barryw/paperlessmcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/barryw/paperlessmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/barryw/paperlessmcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/barryw/paperlessmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/barryw/paperlessmcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,119 This file is loaded in full into every session.

When invoked 1,119 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01119	$0.01119
Opus 5.5	$0.00448	$0.00448
Sonnet 5.5	$0.00224	$0.00224
Haiku 4.5	$0.00112	$0.00112

Measured 2mo ago against content hash 321ea877a46c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

PaperlessMCP CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build & Test Commands

dotnet build                # Build the solution
dotnet test                 # Run all tests
dotnet test --filter "FullyQualifiedName~DocumentToolsTests"  # Run specific test class
dotnet test --logger "console;verbosity=detailed"             # Verbose test output

Running locally:

# Set required environment variables
export PAPERLESS_BASE_URL=https://your-instance.com
export PAPERLESS_API_TOKEN=your-token

# stdio mode (for Claude Desktop)
dotnet run --project PaperlessMCP -- --stdio

# HTTP mode (runs at http://localhost:5000/mcp)
dotnet run --project PaperlessMCP

Architecture

PaperlessMCP is an MCP (Model Context Protocol) server that bridges Paperless-ngx with AI assistants. It supports dual transport modes: stdio for Claude Desktop integration and HTTP for remote usage.

Key Components

Program.cs - Entry point with dual transport setup (stdio vs HTTP). Configures DI, HttpClient with Polly retry policies, and MCP server registration.
Client/PaperlessClient.cs - Central API client for all Paperless-ngx operations. Uses snake_case JSON serialization to match API conventions.
Client/PaperlessAuthHandler.cs - DelegatingHandler that injects API token authentication.
Tools/ - MCP tool implementations, one file per entity type:
- DocumentTools.cs - Search, CRUD, bulk operations, upload (base64 and file path)
- TagTools.cs, CorrespondentTools.cs, DocumentTypeTools.cs, StoragePathTools.cs - Entity management with matching algorithms
- CustomFieldTools.cs - Custom field definitions and assignments
- HealthTools.cs - Ping and capabilities
Models/ - Request/response DTOs organized by entity (Documents/, Tags/, etc.). Uses PaginatedResponse<T> for list endpoints.

Configuration

Environment variables (take precedence over appsettings.json):

PAPERLESS_BASE_URL / PAPERLESS_URL - Paperless-ngx instance URL
PAPERLESS_API_TOKEN / PAPERLESS_TOKEN - API authentication token
MAX_PAGE_SIZE - Max items per page (default: 100)
MCP_PORT - HTTP server port (default: 5000)
HTTP_TIMEOUT_SECONDS - Timeout for Paperless API requests (default: 30)

Read the full file on GitHub · 96 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 96 lines · 1,119 tokens per session scan A 321ea877a46c

Subscribe to this mod's changes

PaperlessMCP CLAUDE.md is an instructions file published in the GitHub repository barryw/PaperlessMCP (50 stars, last pushed 4d ago), licensed MIT. It adds 1,119 tokens to every session, about $0.0045 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Documents mcp paperless

PaperlessMCP CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
PaperlessMCP CLAUDE.mdbarryw/PaperlessMCP	Instructions file	50	4d ago	MIT	A	1,119	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

PaperlessMCP: Instructions file for Claude Code