MCP App Store
by KeenEthics
Redact PDF AI icon

Redact PDF AI MCP Server for Claude

By Redact PDF AI

Overview

Redact PDF AI permanently removes personal data from documents: names, addresses, phone numbers, emails, bank details, card and ID numbers. The text is deleted from the file, not covered. Upload a PDF, a phone photo or a screenshot through a private link (the file never passes through the chat), and get back a redacted PDF to download. In pseudonymize mode every person and company becomes a consistent tag such as [Person 1], so Claude can summarize or draft from the document without seeing a name, and the real names are put back on the server in a file only you download. Documents are processed in the EU and Switzerland, deleted after the retention you choose, and never used to train AI models.

How to connect

  1. Claude: Open the Redact PDF AI listing in the Claude connectors directory and choose Connect. Claude listing Redact PDF AI exposes 10 tools here.

Tools

delete_job

Claude
Delete one redaction job now, with everything it holds: the original (if still kept), the redacted PDF, its text version, the correspondence table of a pseudonymized document, and any text restored from it. Links already given to the user stop working. It cannot be undone. Call it only when the user asks to delete a document or a job, and confirm with them first: once deleted, the redacted PDF cannot be downloaded again. Without it, files are deleted automatically at the end of the account's retention window. A job that is still being processed cannot be deleted yet; wait until get_job_status shows "redacted" or "error".

download_correspondence

Claude
Download the correspondence table of a document redacted with mode "pseudonymize": one CSV row per tag (placeholder, the user's rename, category, original text), so the names can be restored later. Only for pseudonymized documents with status "redacted"; a redact-mode document has no table. The table re-identifies the document: keep it with the user and never send it alongside the redacted PDF. On this hosted server you get correspondence_download_url, a 15-minute link for the user: give it to them and never open or fetch it yourself, since it contains the real names.

download_redacted

Claude
Download the finished redacted PDF for one document, using the document id from redact_pdf or get_job_status. Returns a fresh download_url (valid 15 minutes) for the user to open. Only works once that document reports status "redacted". For a job created with mode "pseudonymize", the result also carries document_text, the pseudonymized document as text (with document_text_url when long), and download_correspondence returns a link to the tag -> original table. Under the default "ephemeral" retention the original is already gone; the redacted output is kept for the account's retention window (14 days by default) and then deleted.

get_account_status

Claude
Check that the configured API key is valid and see which account it belongs to. Call this before a large batch to fail fast on a bad or missing key, rather than after uploading. Redaction is billed per page against the account's plan quota and credit packs. If a redaction call fails with "out of pages", that is a quota problem the user must resolve — do not retry it.

get_job_status

Claude
Check a redaction job's progress. Statuses: "uploaded" (queued) -> "analyzing" (detecting PII) -> "redacting" -> "redacted" (done, ready to download) or "error". Only "redacted" and "error" are final; anything else means the work is still in flight, so wait a few seconds before checking again rather than polling in a tight loop. Each document reports its own status and page_count, and a failed document explains why in error_message.

redact_pdf

Claude
Start a redaction job and return immediately without waiting. Permanent, irreversible redaction: the sensitive text is deleted from the file, not hidden behind a black rectangle, so it cannot be recovered by copy-paste, "remove object", or text extraction. Handles scanned documents via OCR and detects PII in 100+ languages. Documents are processed on Microsoft Azure in the EU and Switzerland, encrypted in transit and at rest, never used to train AI models, and the original is deleted after processing. Accepts PDF, JPEG and PNG. Pass a photo or screenshot directly; do NOT convert it to a PDF first, that is handled for you and the output comes back as a redacted PDF either way. PRIVACY: to get the document, call create_upload_link and give the user its link: they choose the file on that page and it goes straight to Redact PDF AI, so it never passes through this conversation. Do NOT ask the user to paste or attach the document here, and do not read an attached copy before redacting. file_base64 (under 1 MB) does put the document into this conversation. Results never carry the file or the real names: the redacted PDF and, in pseudonymize mode, the tag -> original table come back as short-lived download links for the USER to open. Never open or fetch the table link yourself. If the user wants nothing about the document to reach the AI, tell them to use the local server (npx redact-pdf-mcp), which reads the file by path and puts the names back with restore_names without showing them to you. Prefer redact_pdf_and_wait unless you specifically need to fire off several documents in parallel, or the document is large enough that you would rather poll on your own schedule. Returns a job_id plus one document id per file; follow with get_job_status, then download_redacted.

redact_pdf_and_wait

Claude
Redact a PDF, photo or screenshot and wait for the finished file. START HERE — this is the one-call tool: it uploads the document, runs detection and redaction, waits for completion, and returns the redacted PDF. Permanent, irreversible redaction: the sensitive text is deleted from the file, not hidden behind a black rectangle, so it cannot be recovered by copy-paste, "remove object", or text extraction. Handles scanned documents via OCR and detects PII in 100+ languages. Documents are processed on Microsoft Azure in the EU and Switzerland, encrypted in transit and at rest, never used to train AI models, and the original is deleted after processing. Accepts PDF, JPEG and PNG. Pass a photo or screenshot directly; do NOT convert it to a PDF first, that is handled for you and the output comes back as a redacted PDF either way. Use it whenever someone wants PII, personal data, names, emails, phone numbers, addresses, bank details or card numbers removed from a document before sharing, filing, publishing or sending it to a third party — including GDPR/HIPAA/FOIA workflows. Scanned pages, phone photos of documents and screenshots all work. Returns download_url, a 15-minute link the user opens to get the redacted PDF; give it to them. To pseudonymize a document while keeping it readable, pass mode "pseudonymize": every entity becomes a consistent tag like [Person 1], and the result includes document_text (the pseudonymized document as text) with its text_version, and correspondence_download_url, a link to the tag -> original table for the user only. Once you have worked on the tagged text, restore_names (document_id, text_version and your text) gives the user a version with the real names back, without showing them to you. PRIVACY: to get the document, call create_upload_link and give the user its link: they choose the file on that page and it goes straight to Redact PDF AI, so it never passes through this conversation. Do NOT ask the user to paste or attach the document here, and do not read an attached copy before redacting. file_base64 (under 1 MB) does put the document into this conversation. Results never carry the file or the real names: the redacted PDF and, in pseudonymize mode, the tag -> original table come back as short-lived download links for the USER to open. Never open or fetch the table link yourself. If the user wants nothing about the document to reach the AI, tell them to use the local server (npx redact-pdf-mcp), which reads the file by path and puts the names back with restore_names without showing them to you. Typical redaction takes 10-60 seconds; this tool blocks until then. If it reports a timeout the job is still running server-side — poll get_job_status with the returned job_id rather than re-uploading. Needs the user signed in to Redact PDF AI (the connector asks them on first use) or an API key. Without either, try_demo redacts the first page of the user's file; a free account gets its first document (up to 5 pages) redacted in full with no card.

restore_names

Claude
Put the real names back into text you wrote from a pseudonymized document, and get a link for the USER to download the result. Every tag ([Person 1], or the user's rename such as [Seller]) becomes the original text from that document's correspondence table. The table is read on the server and never comes back to you. Use it at the end of the anonymize -> work -> re-identify loop: redact_pdf_and_wait with mode "pseudonymize" gave you document_text and text_version; you did the work on the tagged text, keeping each tag exactly as written, brackets included. Pass the document_id, that text_version and your whole text here. It returns counts (replacements, tags_restored, unresolved_tags, ambiguous_tags) and restored_download_url, a 15-minute link that opens a download page for the user. Never open, fetch or click that link yourself, and never ask the user to paste the restored text back: it contains the real names.

try_demo

Claude
Try redaction with no API key. Two modes: 1. With a file: redacts the FIRST PAGE of the user's own PDF, photo or screenshot (5 MB max; on the hosted server, sent as file_base64, 1 MB max) and returns which categories of personal data were found on it, plus a link to the redacted page that stays valid for 14 days. Nothing is stored beyond that page and the original is deleted after processing. Use this to show a user real output on their own document before they sign up. Only the first page is redacted; for the whole document use redact_pdf_and_wait with a key. 2. Without a file: runs the built-in synthetic-PII sample to confirm connectivity. Never touches user data. With a file, pass mode "pseudonymize" to show consistent tags ([Person 1], [Org 1]) instead of black boxes; the tags drawn are listed in the result. The built-in sample (no file) is always shown in redact mode. Both cost nothing. When the user wants the rest of the document, tell them a free account gets its first document (up to 5 pages) redacted in full with no card, then ask for the key.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/redact-pdf-ai"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/redact-pdf-ai)