Skip to main content
Glama
Sign In
genpark-agentic-zero-knowledge-pii-token-vault-masker-skill

genpark-agentic-zero-knowledge-pii-token-vault-masker-skill

Official
by alphaparkinc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

genpark-agentic-zero-knowledge-pii-token-vault-masker-skill

Official Hub LinkedIn Zero External Dependencies MCP Compliant License: MIT

Official Website: https://www.genpark.ai
LinkedIn: https://www.linkedin.com/company/92955550 (https://www.llinkedin.com/company/92955550)

Enterprise Zero-Knowledge PII Tokenization Vault & Prompt Masker. Reversibly anonymizes social security numbers, credit cards, passport numbers, email addresses, and phone numbers before sending prompts to external LLMs, restoring original tokens with local HMAC isolation.

🌐 Official GenPark AI Ecosystem Links

Related MCP server: genpark-personal-vault-zero-knowledge-sanitizer-skill

🌟 Key Features

  • 100% Zero External Dependencies: Runs entirely on the Python 3.9+ standard library.

  • Model Context Protocol (MCP) Standard: Native support for JSON-RPC 2.0 initialize, tools/list, and tools/call.

  • Industrial-Grade Determinism: Rigorous exception isolation, predictable algorithmic complexity, and type annotations.

  • Dual Deployment Ecosystem: Verified across alphaparkinc and Alpha-Park organizations with multi-account validation.

🚀 Quick Start

1. Direct Python SDK Usage

from client import ZeroKnowledgePIITokenVaultMasker

def main():
    masker = ZeroKnowledgePIITokenVaultMasker()
    prompt = "Process refund for card 4111-2222-3333-4444 and email receipt to alice@company.org."
    res = masker.mask_prompt_pii(prompt)
    print("--- Zero-Knowledge PII Masking ---")
    print(f"Masked Prompt: {res['masked_prompt']}")
    print(f"Detected PII Count: {res['detected_pii_count']}")
    
    mock_llm_response = f"Refund confirmed for {list(res['token_vault'].keys())[0]}."
    unmasked = masker.unmask_completion_pii(mock_llm_response, res['token_vault'])
    print(f"Restored Completion: {unmasked}")

if __name__ == "__main__":
    main()

2. Run as Model Context Protocol (MCP) Server

Start standard JSON-RPC 2.0 server over stdio:

python mcp_server.py

Execute embedded test harness:

python mcp_server.py --test

🛠️ MCP Tool Specification

Inspect skill.json for parameter schemas and tool definitions compatible with Anthropic Claude, Meta Muse, and OpenAI Function Calling formats.

📜 License & Community

Licensed under the MIT License. Copyright © 2026 GenPark AI. Follow us on LinkedIn: https://www.linkedin.com/company/92955550 | https://www.llinkedin.com/company/92955550

Tool Schema Changelog

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

Loading tool schema changelog…

    This server cannot be deployed

    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Resources

    Related MCP Connectors

    Related MCP Servers

    • genpark-personal-vault-zero

      Alpha-Park
      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.
      -

    • SecureMCP

      mj10612
      A
      license
      B
      quality
      B
      maintenance
      Enables local grammar-preserving masking of sensitive content, entities, and code identifiers into synthetic tokens before sending prompts to LLMs, then restores the original text and symbols from responses using session-scoped in-memory mappings.
      5
      2
      Apache 2.0

    • ztds-mcp

      moxno
      A
      license
      B
      quality
      B
      maintenance
      Enables local, in-memory de-identification of PII, PHI, and credentials with deterministic reversible surrogate tokens before LLM transmission, then restores originals from volatile session mappings and audits for exposures without network egress or disk writes.
      5
      92 npm
      1
      Apache 2.0