# LLM Data Guard: PII & Secrets Redaction

> LLM Data Guard: PII & Secrets Redaction is a paid MCP server for security. Detect and redact PII and API secrets in text, HTML or PDF before it reaches an LLM. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Platforms:** API
- **Website:** https://getfairquery.com/posts/redact-pii-secrets-before-sending-data-to-llm/
- **Repository:** https://github.com/fairquery/llm-data-guard-pii-secrets
- **MCP Registry name:** io.github.fairquery/llm-data-guard-pii-secrets
- **Categories:** security, AI models and LLM tooling
- **Listing updated:** 2026-11-15

## About

Redaction here is a round trip: each hit is swapped for a numbered placeholder such as [EMAIL_1], the redacted text goes to the model, and a restore mode puts the real values back into the answer afterwards. The Apify Actor behind this server handles batches, URLs and PDFs with a text layer up to 10 MB each, with no OCR.

Detection covers emails, phones, card numbers checked by Luhn, IBANs, SSNs, UK national insurance numbers and IP addresses, plus secrets such as private keys, AWS, GitHub, Slack, Stripe, OpenAI and Anthropic keys, JWTs and a generic entropy-based rule. Names, locations and street addresses are optional. Overlaps are resolved by priority so a card number is never also reported as a phone.

The Fairquery article also points to free local tools, pii_scan_text and pii_redact_text, in a separate agent-trust MCP package.

## Features

- **Placeholder redaction:** Replaces findings with numbered tokens and a placeholder map.
- **Secret detection:** Gitleaks-style rules for common cloud and API keys.
- **Validated PII rules:** Luhn, IBAN mod-97 and libphonenumber checks cut false hits.
- **URL and PDF input:** Fetches public pages and PDFs with a text layer.
- **Consistent placeholders:** Reuses tokens across a whole dataset for RAG or fine-tuning.
- **Restore mode:** Swaps original values back server-side.

## Good for

- Clean support tickets before summarising them
- Scrub logs of leaked keys
- Prepare a dataset for fine-tuning
- Block prompts that contain secrets

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http llm-data-guard-pii-secrets 'https://mcp.apify.com/?tools=fetch-actor-details,fairquery/llm-data-guard-pii-secrets'
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.apify.com/?tools=fetch-actor-details,fairquery/llm-data-guard-pii-secrets
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "llm-data-guard-pii-secrets": {
      "url": "https://mcp.apify.com/?tools=fetch-actor-details,fairquery/llm-data-guard-pii-secrets"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "llm-data-guard-pii-secrets": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=fetch-actor-details,fairquery/llm-data-guard-pii-secrets"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "llm-data-guard-pii-secrets": {
      "serverUrl": "https://mcp.apify.com/?tools=fetch-actor-details,fairquery/llm-data-guard-pii-secrets"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "llm-data-guard-pii-secrets": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=fetch-actor-details,fairquery/llm-data-guard-pii-secrets"
    }
  }
}
```

## FAQ

### What does it cost?

$1.50 per 1,000 documents plus $0.20 per 1,000 findings and a $0.05 per 1,000 runs start fee.

### Does it detect names?

Yes, optionally, as low-confidence PERSON findings.

### Does it read scanned PDFs?

No. It uses the text layer only, without OCR.

### Is there a free option?

The article describes free local tools in @fairquery/agent-trust-mcp.

### Is LLM Data Guard: PII & Secrets Redaction free?

No. LLM Data Guard: PII & Secrets Redaction is a paid product.

### How do I add LLM Data Guard: PII & Secrets Redaction to Claude Code?

Run this command in your terminal: claude mcp add --transport http llm-data-guard-pii-secrets 'https://mcp.apify.com/?tools=fetch-actor-details,fairquery/llm-data-guard-pii-secrets'

### What are the best alternatives to LLM Data Guard: PII & Secrets Redaction?

The closest alternatives to LLM Data Guard: PII & Secrets Redaction are REA, Claude Code Ultimate Guide, Agent Roast, Midplane and Leash.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [SecureCloud](https://ai-powered.com/mcp/securecloud): SecureCloud is a free MCP server for security.
- [Tinplate Edge AI Safety, Security & EU Compliance](https://ai-powered.com/mcp/tinplate-edge-ai-safety-security-and-eu-compliance): Tinplate Edge AI Safety, Security & EU Compliance is a freemium MCP server for security.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.

---
Source: https://ai-powered.com/mcp/llm-data-guard-pii-and-secrets-redaction
