PDF Redaction MCP

Redact and detect PII in PDFs directly from Claude Desktop, Claude Code, Cursor, or any MCP-compatible client.

PDF Redaction exposes its PII detection and redaction engine as an MCP (Model Context Protocol) server. This lets any MCP-compatible AI client — Claude Desktop, Claude Code, Cursor, and others — call PDF redaction tools directly as part of an agent's toolset, without writing any REST integration code.

Endpoint

https://api.pdf-redaction.com/mcp/

The server uses the Streamable HTTP transport and is served alongside the existing REST API.

Authentication

Every tool call takes an api_key argument. Generate a key at pdf-redaction.com/apikeys, and check remaining credits/usage at pdf-redaction.com/apikeys/usage.

Calls with an invalid key or exhausted credits return an MCP tool error describing the problem (e.g. Invalid API Key or Credits exhausted).

Free tier limits

10 pages per request
100 free pages per month
5 requests per minute

Configuring your client

Claude Desktop / Claude Code

Add the server to your MCP client configuration (e.g. claude_desktop_config.json, or via claude mcp add for Claude Code):

{
  "mcpServers": {
    "pdf-redaction": {
      "url": "https://api.pdf-redaction.com/mcp/"
    }
  }
}

Cursor

Add the server to .cursor/mcp.json:

{
  "mcpServers": {
    "pdf-redaction": {
      "url": "https://api.pdf-redaction.com/mcp/"
    }
  }
}

Once connected, pass your API key as the api_key argument on each tool call (see below).

Available tools

`anonymize_pdf`

Detects PII in a PDF and returns a redacted copy of the document.

Parameter	Type	Default	Description
`pdf`	`string`	—	Base64-encoded PDF document
`api_key`	`string`	—	Your PDF Redaction API key
`tags`	`Tags[]`	all tags	PII tags to detect and redact
`force_ocr`	`bool`	`false`	Force OCR even if text is extractable
`rotated_text`	`bool`	`false`	Detect and recognize rotated text
`redact_text`	`bool`	`true`	When `false`, PII is detected but not redacted from the returned PDF
`min_chunk_size`	`int`	`0`	Minimum chunk size for text processing
`ocr_langs`	`Langs[]`	—	OCR languages
`custom_tags`	`string[]`	—	Additional custom tags to detect/redact

Returns: { pdf, detected_pii, processing_time } — pdf is the base64-encoded redacted document.

`detect_pii_pdf`

Detects PII in a PDF without redacting it.

Parameter	Type	Default	Description
`pdf`	`string`	—	Base64-encoded PDF document
`api_key`	`string`	—	Your PDF Redaction API key
`tags`	`Tags[]`	all tags	PII tags to detect
`force_ocr`	`bool`	`false`	Force OCR even if text is extractable
`rotated_text`	`bool`	`false`	Detect and recognize rotated text
`ocr_langs`	`Langs[]`	—	OCR languages
`custom_tags`	`string[]`	—	Additional custom tags to detect

Returns: { detected_pii, processing_time }

`anonymize_pdf_custom`

Redacts a PDF using a free-form natural-language instruction instead of a predefined tag list.

Parameter	Type	Description
`pdf`	`string`	Base64-encoded PDF document
`prompt`	`string`	e.g. `"Redact all dates, names, and email addresses"`
`api_key`	`string`	Your PDF Redaction API key

Returns: { pdf, detected_pii, processing_time }

Supported tags

DATE, PERSON_NAME, ORGANIZATION, LOCATION, EMAIL, PHONE, ID, ACCOUNT, ZIP_CODE, ADDRESS, IP, URL, SSN, DRIVER_LICENSE, PASSPORT, PASSWORD, AGE, CREDIT_CARD, MONEY_AMOUNT, SIGNATURE, QR_CODE, FACE

Supported OCR languages

eng, spa, fra, deu, ita, por, rus

Redact PDFs from your favorite AI client

Generate an API key and connect the PDF Redaction MCP server to Claude Desktop, Claude Code, Cursor, or any MCP-compatible client.

Get an API Key