Log inSubmit server
Redact Pdf MCP logo

Redact Pdf MCP

Permanently redacts PII from PDFs and scans with OCR, pseudonymization, batch jobs, and local name restoration.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Redact Pdf MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "redact-pdf-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "redact-pdf-mcp"
      ],
      "env": {
        "REDACT_PDF_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 9 tools correctly (Today).

Overview

redact-pdf-mcp MCP server uploads PDFs or images to a redaction service that detects and permanently removes sensitive text, including content found through OCR. It supports one-call processing, asynchronous jobs for multiple documents, pseudonymization with consistent placeholders, and a keyless first-page demo. Reach for it when an agent needs to produce a shareable PDF whose underlying text cannot be recovered, rather than merely hiding text with a visual overlay.

Use cases

  • Redact personal data from contracts before sharing them
  • Anonymize documents before sending them to another AI
  • Process multiple statement PDFs in parallel
  • OCR and redact scanned documents or document photos
  • Restore pseudonymized names in locally generated files

Key features

  • Permanent PDF and image redaction
  • OCR for scanned documents
  • Pseudonymization with consistent tags
  • Asynchronous batch jobs
  • Keyless first-page demo
  • Local name restoration

Tools9

What Redact Pdf MCP lets your agent do. Expand a tool for its parameters.

Verified live~5.6k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

9/9 checks healthy over the last 48d

What it can do

From the 9 tools this server returned when we ran it; 9 declare their own safety hints.

Can delete or modify data · 5Handles credentials · 4Makes network requests · 8Read-only tools · 4
Unusual tool instructions. 3 tool descriptions contain text aimed at the AI model rather than at you (tries to chain into other tools; asks the assistant to hide something from the user). Read the tool descriptions before connecting.
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age60 days
Maintainers1

Observed 2026-10-30 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · redact-pdf-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars1Stargazers on the source repository.
npm downloads1kPackage downloads in the last 30 days.
Last commit5d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed9Callable tools this server registers over MCP.

How Redact Pdf MCP works

What redact-pdf-mcp MCP server does

redact-pdf-mcp MCP server belongs in the 🔒 Security category and handles document-level PII protection. It accepts PDFs, JPEGs, and PNGs, then returns a PDF with detected sensitive content removed from the document rather than covered by a rectangle. Page rasterization removes the text layer and metadata associated with the source, so ordinary text extraction, copying, or object removal cannot recover the redacted content.

OCR is applied to image-only PDFs and document photos before detection. The service identifies Person, Email, PhoneNumber, Address, Organization, Date, IBAN, and CreditCard entities, and supports custom terms that should always or never be redacted. Detection supports more than 100 languages according to the project documentation.

A pseudonymization mode replaces detected entities with repeatable labels such as [Person 1] or [Org 1]. This keeps the document readable while removing the original text. The processing response can include a tag-to-original CSV table, while the local restore_names tool can put names back into agent-produced Markdown, text, or DOCX files without returning the names itself.

How it works

The redact_pdf_and_wait tool uploads a document, waits for processing, and returns the completed result in one operation. For parallel or longer-running work, redact_pdf starts a job and get_job_status reports its progress through uploaded, analyzing, redacting, and redacted. download_redacted retrieves the finished file, and download_correspondence retrieves the pseudonymization mapping.

try_demo works without an API key. With a supplied file, it processes only the first page; without a file, it runs a built-in sample. Full processing uses an API key. Documents are processed in the EU and Switzerland on Microsoft Azure, with TLS 1.2 or later in transit and AES-256 at rest. The documentation states that content is not used to train AI models and that the original is deleted after processing under the default ephemeral retention setting. Redacted outputs are retained for 14 days by default, with configurable retention.

Setup and configuration

Install the redact-pdf-mcp MCP server through npm with npx -y redact-pdf-mcp. Claude Code, Claude Desktop, Cursor, and VS Code examples are provided in the project documentation. Set REDACT_PDF_API_KEY in the MCP client's environment for full access; the key takes priority over local configuration.

get_account_status can validate the account before a batch. If a client cannot pass environment variables, set_api_key checks and stores a user-only key locally when supported, without returning the key. A client with MCP elicitation can request confirmation before saving it. The key is stored under the user's configuration directory and is not silently replaced when an existing key remains valid.

Tools and capabilities

  • Permanently redact supported PII from PDFs and images.
  • OCR scanned documents and photos before detection.
  • Process one document synchronously or submit jobs for parallel processing.
  • Pseudonymize entities with consistent placeholders and retrieve the correspondence table.
  • Run a keyless first-page or built-in demo.
  • Restore names locally in agent-created .md, .txt, or .docx files.
  • Check account status and configure an API key through MCP.

Limitations and notes

The keyless demo is limited to a real file's first page; other operations require an API key. Detection is model-based, so custom always-redact and never-redact term lists are available for cases the built-in entity types do not cover. retention: "studio" keeps detected masks for human review and adjustment before export.

The redact-pdf-mcp MCP server does not provide a local-only PDF redaction pipeline: documents are sent to the hosted processing service. The project states that its own MCP server sends no telemetry, but hosted processing, retention, and account requirements still apply. Its infrastructure is described as certified under several Azure frameworks; the project itself is not independently audited for those frameworks.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Redact Pdf MCP

redact-pdf-mcp is an MCP server that connects an AI agent to a hosted PDF redaction service. Its main tools upload and process documents, check job status, download redacted files, pseudonymize detected entities, run a keyless demo, restore names locally, and manage API-key access.

Install it with `npx -y redact-pdf-mcp` through your MCP client configuration. The project documents setup commands for Claude Code, Claude Desktop, Cursor, and VS Code. Set `REDACT_PDF_API_KEY` for full processing; `try_demo` works without a key.

Yes, redact-pdf-mcp uses OCR for image-only PDFs and document photos before detecting PII. It also accepts JPEG and PNG files directly and returns a redacted PDF.

Yes, use `mode: "pseudonymize"` to replace detected people, organizations, and addresses with consistent tags. The service can return a tag-to-original table, and `restore_names` can locally restore names in supported Markdown, text, or DOCX files.

Full document processing requires an API key, but `try_demo` is keyless. Without a file it runs a built-in sample; with a file it redacts the first page for demonstration.

Related MCP servers

All in Security All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewRedact Pdf MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/redact-pdf-mcp?style=directory)](https://allmcps.com/mcp/redact-pdf-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/redact-pdf-mcp"><img src="https://allmcps.com/api/badge/redact-pdf-mcp?style=directory" alt="Redact Pdf MCP on AllMCPs" /></a>