masquerade
by postralai·★ 76·Score 43
Masquerade MCP is a privacy firewall for LLMs that redacts sensitive data from PDFs before processing.
Overview
Masquerade MCP is a specialized tool that provides privacy protection for Large Language Models by acting as a data redaction layer. It processes PDF files to automatically detect and redact sensitive information such as names, emails, dates, and entities before the document is sent to an LLM. The tool integrates with Tinfoil AI platform for sensitive data detection and creates redacted versions of documents while providing users with preview capabilities and summaries of what was redacted.
Try asking AI
After installing, here are 3 things you can ask your AI assistant:
When to choose this
Choose Masquerade when working with sensitive PDF documents that need AI analysis but cannot have raw personal information exposed to LLMs.
When NOT to choose this
Don't choose Masquerade if you need to process document formats other than PDFs or if you're concerned about dependency on the Tinfoil service.
Tools this server exposes
1 tool extracted from the READMEredact_pdfRedacts sensitive information from a PDF file.
Comparable tools
Installation
Installation Options
**Option 1: Automated Setup**
curl -O https://raw.githubusercontent.com/postralai/masquerade/main/setup.sh && bash setup.sh**Option 2: Manual Setup**
- Create a virtual environment with Python 3.10-3.12
python3.12 -m venv pdfmcp
source pdfmcp/bin/activate- Install the repo:
pip install git+https://github.com/postralai/masquerade@main- Configure Claude:
python -m masquerade.configure_claude- Add the following to your
claude_desktop_config.json:
{
"mcpServers": {
"pdf-redaction": {
"command": "/path/to/python",
"args": ["/path/to/mcp_pdf_redaction.py"],
"env": {
"TINFOIL_API_KEY": "your_api_key"
}
}
}
}On Hacker News
Recent discussion from the developer community.
- Story by Sam_Eyob · 2025-06-23
- Story by julesdrean · 2025-06-24
Compare masquerade with
Last updated · Auto-generated from public README + GitHub signals.