postralai/masquerade

🤐 **Problem:** Tools like Claude or GPT are incredibly powerful, but they require raw input. If you're dealing with contracts, medical records, or internal documents, that's risky.
🛡️ **Solution:** Masquerade acts as a privacy firewall for your files. Just paste in the **file path** to a PDF, and Masquerade will:
- Automatically detect sensitive data (names, emails, dates, entities)
- Redact the sensitive data
- Let you preview before sending to an LLM
Architecture
1. **User Input**: The user asks Claude to redact a PDF by providing its file path.
1. **PDF Processing**: MCP reads the PDF and converts it to text.
1. **Sensitive Data Detection**: The text is sent to Tinfoil (an isolated AI platform using Llama 3.3 70B) to identify sensitive data.
1. **Redaction**: MCP removes the sensitive data and creates a redacted PDF.
1. **Summary Return**: MCP sends Claude a summary with:
- Masked versions of the sensitive data
- Redaction counts per page
- The path to the redacted file
1. **Quering PDF with Claude**: The user can upload the redacted PDF to Claude if satisfied with the redactions.
Installation
1. Install Claude desktop
1. Get Tinfoil API key (create account and API key)
1. Configure environment
Option 1: Automated
4. Restart Claude desktop app (if successfully configured)
Option 2: Manual (click to expand)
4. Create a virtual environment with **Python ">=3.10,
How to use?
1. Prompt Claude: "Redact sensitive information from this PDF: /path/to/filename.pdf"
1. MCP opens the redacted and highlighted PDF files
1. Manually upload the redacted PDF to Claude for quering
**Note:** Don't upload the original PDF to Claude, only the file path.
Contributing
If you have a fix or improvement, feel free to submit a pull request. For significant changes, please open an issue first to discuss your proposed updates.
See the Developer section for the installation of this repository.
License
This project is licensed under the MIT License - see the LICENSE file for details.