Skip to main content
Glama

🛡️ ScrubVault: Zero-Data-Leak AI Airgap & Reversible PII Masking Engine

PyPI version License: Apache 2.0 Glama Score M8ven Score Zero Dependencies AgentShield Security Raptor Guard Certified GDPR Art. 32

Send sensitive data to Cloud LLMs (ChatGPT, Claude, Gemini) without ever leaking confidential PII.

pip install scrub-vault

ScrubVault is a lightweight, zero-dependency in-memory privacy proxy and Model Context Protocol (MCP) server. It intercept prompts, replaces personal identifiable information (emails, IBANs, IP addresses, credit cards, tax IDs) with deterministic local tokens ({{EMAIL_1}}, {{IBAN_1}}), and restores the original values when the AI responds.


🚀 The Architecture

                   +----------------------------------+
                   |  Your Prompt (Confidential PII)  |
                   +----------------------------------+
                                     │
                                     ▼
                      ┌─────────────────────────────┐
                      │    ScrubVault (Local RAM)   │
                      │  - Scans & Masks Sensitive  │
                      │  - Stores Mapping in Memory │
                      └─────────────────────────────┘
                                     │
                                     ▼ (Masked Prompt: "{{EMAIL_1}}, {{IBAN_1}}")
                      ┌─────────────────────────────┐
                      │    Public Cloud LLM API     │
                      │   (OpenAI / Anthropic / ...) │
                      │   *Zero PII is transmitted* │
                      └─────────────────────────────┘
                                     │
                                     ▼ (Response with tokens)
                      ┌─────────────────────────────┐
                      │    ScrubVault (Local RAM)   │
                      │  - Deterministic Unmasking  │
                      └─────────────────────────────┘
                                     │
                                     ▼
                   +----------------------------------+
                   |  End-User Result (Restored PII)  |
                   +----------------------------------+

Related MCP server: pseudonym-mcp

⚡ Quickstart

1. Python SDK (Zero Dependencies)

from src.core.vault import ScrubVault

vault = ScrubVault()

# 1. Mask sensitive input
input_text = "Order for client Max, email: max@corp.de, IBAN: DE89370400440532013000"
result = vault.mask(input_text)

print(result.masked_text)
# Output: "Order for client Max, email: {{EMAIL_1}}, IBAN: {{IBAN_1}}"

# 2. Transmit result.masked_text to your LLM of choice...
ai_response = "Received confirmation for {{EMAIL_1}} on account {{IBAN_1}}."

# 3. Unmask locally
clean_response = vault.unmask(ai_response, result.token_map)
print(clean_response)
# Output: "Received confirmation for max@corp.de on account DE89370400440532013000."

2. Standalone CLI

# Calculate GDPR Art. 32 Risk Score
python -m src.cli.main audit "Contract with Herr Schmidt, IBAN: DE89370400440532013000"

# Mask a dataset file directly
python -m src.cli.main scrub-dataset input.json output_clean.json

🤖 Model Context Protocol (MCP) Integration

ScrubVault includes a native stdio Model Context Protocol (MCP) server. Add it to your claude_desktop_config.json or Antigravity configuration:

{
  "mcpServers": {
    "scrub_vault": {
      "command": "python",
      "args": ["-m", "src.mcp.server"],
      "cwd": "/path/to/scrub_vault"
    }
  }
}

1-Click Install via Smithery (Claude Desktop, Cursor):

npx -y @smithery/cli install @tastenkasperle/scrub-vault --client claude

Available MCP Tools:

  • scrub_mask_text: Masks PII in input text and returns a reversible token map.

  • scrub_unmask_text: Replaces tokens with original values.

  • scrub_audit_risk: Calculates risk scores and detection breakdowns.

  • scrub_anonymize_json: Recursively scrubs JSON structures.


🛡️ Security & Clean Code Standard

  • Pure Python Standard Library: Zero third-party dependencies (re, json, sys, typing).

  • In-Memory Vault: Token maps live exclusively in volatile RAM and are never written to disk.

  • ReDoS Hardened: Regex patterns are strictly bounded against algorithmic complexity attacks.

  • Audit Passed: Tested and verified by Raptor Guard SAST (0 Critical, 0 High, 0 Medium findings).


📄 License & Attribution

Apache License 2.0. Engineered and orchestrated by THE HIVE // BSO (Bio-Synthetic Organism).
Provenance & Stewardship: Maintained by C. H. (BSO Steward).

Available Tools

4 tools
scrub_anonymize_jsonC

Recursively scans and anonymizes all PII in a JSON data structure for safe staging or testing.

Inputs: data (required).

scrub_audit_riskB

Audits a text or document for GDPR / DSGVO Art. 32 PII risks and returns an audit score.

Inputs: text (required).

scrub_mask_textA

Masks sensitive PII (emails, phones, IBANs, IPs, tax IDs) from text and generates a local token_map for zero-leakage prompt forwarding.

Inputs: text (required).

scrub_unmask_textC

Restores original sensitive values into an LLM response using the local token_map.

Inputs: text (required), token_map (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool targets a distinct operation: masking text, restoring values, auditing risk, and anonymizing JSON. Mask/unmask are clearly paired complements rather than overlapping, and audit/anonymize are separate concerns.

    Naming Consistency5/5

    All tools use a consistent scrub_ prefix followed by a verb_noun pattern (mask_text, unmask_text, audit_risk, anonymize_json) in uniform snake_case.

    Tool Count5/5

    Four tools is well-scoped for a focused PII-scrubbing server, with mask/unmask round-trip, an audit function, and a JSON variant each earning its place.

    Completeness4/5

    Covers the core lifecycle of mask, unmask, audit, and JSON anonymization with no obvious dead ends. Minor gaps exist around token_map persistence/management and document/file-level operations, but agents can work around these.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Local pseudonymisation MCP server that detects PII in text, replaces it with opaque tokens before sending to cloud LLMs, and restores tokens afterward.
      2
      73 npm
      2
      MIT
    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables agents to encrypt and sanitize sensitive data such as credentials, credit card numbers, and addresses locally before dispatching prompts to cloud LLMs, then rehydrate the masked values client-side. It runs deterministically with zero external dependencies over MCP JSON-RPC stdio, so no plaintext PII leaves the user's machine.
      -