by StabRise · Jupyter Notebook
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
This MCP server, com.pdf-redaction/pdf-redaction-mcp, detects and redacts PII (Personally Identifiable Information) in PDF documents. The server’s scope is focused on processing PDFs to identify personal data and apply redaction to protect sensitive information.
Captured live from the server via tools/list.
Anonymize a PDF by detecting and redacting PII (Personally Identifiable Information). :param pdf: Base64-encoded PDF document to process. :param api_key: API key used to authenticate and meter usage. Generate one at https://pdf-redaction.com/apikeys/. :param tags: PII tags to detect and redact. If empty, all available tags are used. :param force_ocr: Force OCR processing even if text is extractable from the PDF. :param rotated_text: Enable detection and recognition of rotated text. :param redact_text: Enable text redaction using NER. When False, PII is detected but not redacted from the returned PDF. :param min_chunk_size: Minimum chunk size for text processing. :param ocr_langs: OCR languages to use for text recognition. :param custom_tags: Additional custom tags to detect and redact. :return: dict with "pdf" (base64-encoded redacted PDF), "detected_pii", and "processing_time".
| string | required | ||
| api_key | string | required | |
| tags | any | optional | |
| force_ocr | boolean | optional | |
| rotated_text | boolean | optional | |
| redact_text | boolean | optional | |
| min_chunk_size | integer | optional | |
| ocr_langs | any | optional | |
| custom_tags | any | optional | |
| context | string | required | Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization." |
{
"type": "object",
"properties": {
"pdf": {
"type": "string"
},
"api_key": {
"type": "string"
},
"tags": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/Tags"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null
},
"force_ocr": {
"default": false,
"type": "boolean"
},
"rotated_text": {
"default": false,
"type": "boolean"
},
"redact_text": {
"default": true,
"type": "boolean"
},
"min_chunk_size": {
"default": 0,
"type": "integer"
},
"ocr_langs": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/Langs"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null
},
"custom_tags": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null
},
"context": {
"type": "string",
"description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""
}
},
"required": [
"pdf",
"api_key",
"context"
],
"$defs": {
"Langs": {
"description": "OCR languages.",
"enum": [
"eng",
"spa",
"fra",
"deu",
"ita",
"por",
"rus"
],
"type": "string"
},
"Tags": {
"description": "Tags for PII detection and redaction.",
"enum": [
"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"
],
"type": "string"
}
}
}Detect PII (Personally Identifiable Information) in a PDF without redacting it. :param pdf: Base64-encoded PDF document to process. :param api_key: API key used to authenticate and meter usage. Generate one at https://pdf-redaction.com/apikeys/. :param tags: PII tags to detect. If empty, all available tags are used. :param force_ocr: Force OCR processing even if text is extractable from the PDF. :param rotated_text: Enable detection and recognition of rotated text. :param ocr_langs: OCR languages to use for text recognition. :param custom_tags: Additional custom tags to detect. :return: dict with "detected_pii" and "processing_time".
| string | required | ||
| api_key | string | required | |
| tags | any | optional | |
| force_ocr | boolean | optional | |
| rotated_text | boolean | optional | |
| ocr_langs | any | optional | |
| custom_tags | any | optional | |
| context | string | required | Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization." |
{
"type": "object",
"properties": {
"pdf": {
"type": "string"
},
"api_key": {
"type": "string"
},
"tags": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/Tags"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null
},
"force_ocr": {
"default": false,
"type": "boolean"
},
"rotated_text": {
"default": false,
"type": "boolean"
},
"ocr_langs": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/Langs"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null
},
"custom_tags": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null
},
"context": {
"type": "string",
"description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""
}
},
"required": [
"pdf",
"api_key",
"context"
],
"$defs": {
"Langs": {
"description": "OCR languages.",
"enum": [
"eng",
"spa",
"fra",
"deu",
"ita",
"por",
"rus"
],
"type": "string"
},
"Tags": {
"description": "Tags for PII detection and redaction.",
"enum": [
"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"
],
"type": "string"
}
}
}Anonymize a PDF using a custom natural-language prompt instead of predefined tags. :param pdf: Base64-encoded PDF document to process. :param prompt: Custom prompt describing what to detect and redact, e.g. "Redact all dates, names, and email addresses". :param api_key: API key used to authenticate and meter usage. Generate one at https://pdf-redaction.com/apikeys/. :return: dict with "pdf" (base64-encoded redacted PDF), "detected_pii", and "processing_time".
| string | required | ||
| prompt | string | required | |
| api_key | string | required | |
| context | string | required | Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization." |
{
"type": "object",
"properties": {
"pdf": {
"type": "string"
},
"prompt": {
"type": "string"
},
"api_key": {
"type": "string"
},
"context": {
"type": "string",
"description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""
}
},
"required": [
"pdf",
"prompt",
"api_key",
"context"
]
}
Secure Your PDFs with AI-powered Redaction
It is example of using API for https://pdf-redaction.com
Free API for redacting PDFs available at https://api.pdf-redaction.com/api/docs
For generate API Key please go to the: https://pdf-redaction.com/apikeys/
For check usage: https://pdf-redaction.com/apikeys/usage/
usage
Put API Key to the env variable PDF_REDACTION_API_KEY or to .env file.
Limitations for free version:
Option A (curl):
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/StabRise/pdf-redaction-api/main/install.sh)"
Option B (wget):
/bin/bash -c "$(wget -qO- https://raw.githubusercontent.com/StabRise/pdf-redaction-api/main/install.sh)"
| Chapter | Notebook |
|---|---|
| 1: PDF Redaction API | |
| 2: PDF Redaction API base64 | |
| 3: PDF Redaction API using prompt | |
| 4: Redact QR Codes from PDF | |
| 5: Redact Rotated/Vertical text in PDF | |
| 6: Redact Signatures from PDF | |
| 7: Redact Faces from PDF | |
| 8: Redact custom PII data | |
This provides the flexibility to redact PDF using custom prompt.
You can try it out for free at https://pdf-redaction.com
Hosted server - connect over the network, no local install.
https://api.pdf-redaction.com/mcp/claude_desktop_config.json
{
"mcpServers": {
"pdf-redaction-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.pdf-redaction.com/mcp/"
]
}
}
}Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.