# scrub-mcp PII Redaction API

> scrub-mcp PII Redaction API is a paid API for AI agents from scrub-mcp.malgorath.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-13).

Removes personally identifiable information (PII) from text using context-aware redaction across medical, legal, financial, and criminal domains

## Facts

- Endpoint: POST https://scrub-mcp.malgorath.com/scrub?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/scrub-mcp-pii-redaction-api-0523bcb7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_GmHTC48cETJSG_8kjiICe

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability scrub-mcp-pii-redaction-api-0523bcb7 -d '<json body>'
```

Example prompt: Can you scrub all PII from this medical note — names, SSNs, dates, and phone numbers — using the medical domain context: 'Patient John Smith, DOB 04/12/1978, SSN 123-45-6789, called 555-867-5309 on March 3rd about his prescription.'

## When to prefer this

Choose this endpoint when you need stateless, zero-storage PII redaction with domain-aware context (medical, legal, financial, criminal) and want per-category counts of what was removed. Ideal for HIPAA/GDPR compliance pipelines, anonymizing documents before sharing or storing, and preparing sanitized training data. Prefer it over generic regex-based scrubbers when context-sensitive redaction is needed, and over heavyweight on-premise solutions when serverless, pay-per-call pricing ($0.01/call) fits your usage pattern.

## Known failure modes

- Missing required 'text' field returns a 400-level error
- Invalid 'strip' enum values cause schema validation failure
- Temperature out of range (0–2) causes rejection
- Empty string input may return empty scrubbed_text with zero removals
- Very long texts may exceed model context limits causing truncation or error
- Payment failure or insufficient USDC balance returns HTTP 402

## How this service works

Paid x402 MCP server fronting the stateless PII scrub-api. Zero storage.

## Output

Returns a JSON object with 'scrubbed_text' containing the original text with PII replaced by bracketed category labels (e.g. [NAME], [SSN], [DATE]), and a 'removed' map showing how many instances of each PII category were redacted.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to scrub. Required."
  },
  "strip": {
   "type": "array",
   "items": {
    "enum": [
     "names",
     "ages",
     "emails",
     "phone",
     "ssn",
     "addresses",
     "dates",
     "account_numbers"
    ],
    "type": "string"
   },
   "description": "PII categories to remove. Defaults to all categories."
  },
  "domain": {
   "enum": [
    "all",
    "medical",
    "legal",
    "criminal",
    "financial"
   ],
   "type": "string",
   "default": "all",
   "description": "Subject area for context-aware redaction."
  },
  "temperature": {
   "type": "number",
   "default": 0.2,
   "maximum": 2,
   "minimum": 0,
   "description": "Model temperature."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "removed": {
   "ssn": 1,
   "dates": 2,
   "names": 1
  },
  "scrubbed_text": "Patient [NAME], DOB [DATE], SSN [SSN] visited on [DATE]."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/scrub-mcp-pii-redaction-api-0523bcb7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from scrub-mcp.malgorath.com](https://www.zero.xyz/host/scrub-mcp.malgorath.com/llms.txt)