redact-pdf-mcp
This server permanently removes sensitive text from PDFs (and images) by deleting it from the file rather than covering it, so the data cannot be recovered.
Redact PDFs and images: Upload a PDF, JPEG, or PNG and get back a redacted PDF with text permanently removed.
OCR for scanned documents: Handles image-only PDFs and photos of documents.
Detect PII in 100+ languages: Person, Email, PhoneNumber, Address, Organization, Date, IBAN, CreditCard.
Custom redaction rules: Always-redact and never-redact term lists, plus restriction to specific PII categories.
One-call or async workflows:
redact_pdf_and_waitblocks until done;redact_pdfstarts a job and returns immediately for parallel work.Check job status: Poll
uploaded → analyzing → redacting → redactedorerror, with per-document page counts and error messages.Download finished redacted PDFs: Fetch output by document ID; writes atomically and never overwrites existing files.
Try without an API key:
try_demoruns a keyless demo on synthetic data to verify the server works.Verify account and quota:
get_account_statuschecks the API key and account before large batches.Human review option:
retention: "studio"keeps detected masks for manual approval before export.Idempotent redaction: Repeating an identical call returns the same job, preventing double redaction and double billing.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@redact-pdf-mcpRedact the personal data in ~/Documents/contract.pdf"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Redact PDF MCP server
An MCP server that permanently redacts PII from PDFs. Give an agent a PDF, get back a PDF with the sensitive text removed from the file — not covered with a black rectangle that anyone can select, copy, or delete.
Most "redaction" MCP servers scrub PII out of prompt text. This one takes a real document and returns a real redacted document.
claude mcp add redact-pdf -- npx -y redact-pdf-mcpThen ask: "Redact the personal data in ~/Documents/contract.pdf".
Try it with no API key
The server ships a keyless tool, try_demo, so you can verify the whole path — client,
server, API — before signing up for anything:
You: Use the redact-pdf server's try_demo tool.
Claude: The demo redacted a synthetic sample and removed 5 entities: Person (
Jane Sample), Email (jane.sample@example.com), PhoneNumber (+1 415 555 0142), Organization (Globex Demo Inc.), Date (2026-03-14).
Same thing from a terminal, no install:
curl https://www.redact-pdf.ai/v1/demoRelated MCP server: Nutrient Document Engine MCP Server
What it does
Permanent, irreversible redaction. The underlying text is deleted, not masked. It cannot be recovered by copy-paste, text extraction, or "remove object" in a PDF editor.
PDFs and images. Pass a PDF, JPEG or PNG. Photos and screenshots do not need converting first; the output is a redacted PDF either way.
Scanned documents. OCR handles image-only PDFs and photos of documents.
100+ languages for entity detection.
Eight entity types: Person, Email, PhoneNumber, Address, Organization, Date, IBAN, CreditCard — plus your own always-redact and never-redact term lists.
EU/Swiss processing.
Human review when it matters.
retention: "studio"keeps the detected masks so a person can check and adjust them before export.
Install
Claude Code
claude mcp add redact-pdf --env REDACT_PDF_API_KEY=your_key -- npx -y redact-pdf-mcpClaude Desktop
claude_desktop_config.json:
{
"mcpServers": {
"redact-pdf": {
"command": "npx",
"args": ["-y", "redact-pdf-mcp"],
"env": { "REDACT_PDF_API_KEY": "your_key" }
}
}
}Cursor
.cursor/mcp.json:
{
"mcpServers": {
"redact-pdf": {
"command": "npx",
"args": ["-y", "redact-pdf-mcp"],
"env": { "REDACT_PDF_API_KEY": "your_key" }
}
}
}VS Code
code --add-mcp '{"name":"redact-pdf","command":"npx","args":["-y","redact-pdf-mcp"],"env":{"REDACT_PDF_API_KEY":"your_key"}}'Get an API key at redact-pdf.ai/sign-up. Without one,
try_demo still works; everything else will tell the agent to ask you for a key.
Tools
Tool | What it does |
| Start here. Upload, redact, wait, return the finished PDF. One call. |
| Start a job and return immediately, for redacting several documents in parallel. |
| Poll a job: |
| Fetch the redacted output for one document. |
| Keyless. Verify the server works with zero configuration. |
| Check the API key is valid and see the account, before a big batch. |
Redaction rules, on either redact tool:
Argument | Effect |
| Restrict to specific entity types. Omit for account defaults. |
| Always redact these, even if not detected as PII (codenames, case numbers). |
| Never redact these, even if detected (your own company name). |
|
|
Remote server
The package also ships a streamable-HTTP server for hosted use, where the API key travels per request instead of in the environment:
npx redact-pdf-mcp-http # listens on :8080/mcpPOST /mcp
X-API-Key: your_key (or: Authorization: Bearer your_key)It is stateless — no sessions, no stored keys, nothing kept between requests — so each request gets its own short-lived server instance and one caller's key can never leak into another's tool call.
The handshake, tools/list, and try_demo work without a key, so a client can connect and
verify the server before anyone signs up; every other tool returns 401 with a
WWW-Authenticate challenge.
Documents are supplied as file_base64 (the remote server has no access to your
filesystem).
Fetching a document by URL is off by default on the remote server. The address check is real — URLs resolving to loopback, private, or link-local addresses are refused, and every redirect hop is re-checked — but the socket resolves the hostname a second time after that check, so a DNS-rebinding attacker with a short TTL can still have the server validate one address and connect to another. Closing that requires pinning the connection to the validated address, which is not implemented yet, so an internet-reachable server does not offer the surface at all.
Set REDACT_PDF_ENABLE_URL_INPUT=1 to accept file_url, and only where you have your own
egress controls (a network policy or allowlisting proxy) in front of the server.
REDACT_PDF_ALLOW_PRIVATE_URLS=1 additionally permits private addresses, for a
self-hosted instance fetching from internal storage.
stdio mode is unaffected: it runs on your own machine, where fetching a URL carries no privilege you do not already have.
Variable | Default | Purpose |
| — | API key (stdio mode only; remote takes it per request). |
|
| Point at a different API host. |
|
| HTTP server port. |
|
| HTTP endpoint path. |
| unset | Accept |
| unset | Self-hosted only: permit |
Privacy
No telemetry. The server makes exactly the API calls its tools describe, and nothing else. No analytics, no error reporting, no phone-home.
Stateless. No database, no cache, no disk writes except the redacted PDF you asked for, at the path you asked for.
Your originals stay yours. In stdio mode the input file is read and never modified. Under the default
ephemeralretention the API deletes the original after processing.Idempotent by default. The idempotency key is derived from the file bytes and the redaction settings, so an agent that retries the same call gets the same job back instead of redacting — and billing — twice. That cache lasts 24 hours; pass an explicit
idempotency_keywhen you genuinely want a second, separate redaction of the same file.Never overwrites. In stdio mode the redacted PDF is written atomically and the tool refuses to clobber an existing file.
Limits
50 MB per PDF, 10 MB per image, 100 files per job.
PDF, JPEG and PNG in; always a PDF out. Convert other formats (DOCX, TIFF, HEIC) to PDF first.
On the remote server, base64 inflates a document by about a third, so prefer
file_urlfor anything large.Passing an empty
pii_categorieslist is rejected: to the API an empty list means "redact nothing", which would return an untouched file reported as redacted. Omit the argument to use your account defaults.Billed per page against your plan quota and credit packs. A
quota_exceedederror means top up — the tools tell the agent not to retry it.
Development
npm install
npm run build
npm test # offline unit + tool tests
npm run test:integration # hits the live keyless demo endpoint; no key neededLinks
API docs: redact-pdf.ai/developers
OpenAPI spec: redact-pdf.ai/openapi.yaml
LLM index: redact-pdf.ai/llms.txt
Support questions about redaction quality, billing, or your account go to info@redact-pdf.ai — GitHub issues here are for the MCP server itself.
MIT licensed.
Maintenance
Related MCP Servers
- FlicenseAqualityDmaintenanceEnables loading, reviewing, and redacting sensitive content in PDF documents through text-based or area-based redaction methods. Supports customizable redaction appearance and saves redacted PDFs with comprehensive error handling.72
- AlicenseNot gradedqualityBmaintenanceEnables AI agents and users to process documents through natural language, supporting PDF operations like text extraction, redaction, splitting, form filling, annotations, and content search.20561MIT

@actalumen/mcp-serverofficial
FlicenseAqualityCmaintenanceEnables AI agents to upload, verify, and chat about documents for compliance (e.g., SOC2, GDPR) with PII redacted server-side.810- FlicenseNot gradedqualityDmaintenanceEnables AI agents to redact PII from text, summarize redacted content, and manage custom redaction patterns across multiple languages.
Related MCP Connectors
Turn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
Classify data safety before storing or sharing. GDPR, HIPAA, PCI-DSS, CCPA. AI-powered.
Read PDFs and images as markdown or text, with exact costs and hard spend caps. $0.75/1k pages.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dambuchs/redact-pdf-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server