Masquerade connects an MCP client to a PDF redaction workflow. You give it a file path, it extracts text, sends it to Tinfoil to detect sensitive data, and produces a redacted PDF plus a summary of what was removed. It is meant to keep raw documents out of the LLM prompt while still letting you work with the content.
Builders who want to send PDFs to an MCP-capable agent without exposing names, emails, dates, or other sensitive text.
You can review a redacted PDF and masked summary instead of handing raw confidential documents to your agent.
Reads a PDF from a file path and converts it to text through MCP.
Sends the extracted text to Tinfoil to find names, emails, dates, and entities.
Creates a redacted PDF with the sensitive text removed or masked.
Returns masked examples, per-page redaction counts, and the path to the redacted file.
Includes automated and manual setup steps for wiring the MCP server into Claude desktop.
curl -O https://raw.githubusercontent.com/postralai/masquerade/main/setup.sh && bash setup.sh
python3.12 -m venv pdfmcp source pdfmcp/bin/activate python --version
pip install git+https://github.com/postralai/masquerade@main
python -m masquerade.configure_claude
🤐 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:
curl -O https://raw.githubusercontent.com/postralai/masquerade/main/setup.sh && bash setup.sh
python3.12 -m venv pdfmcp
source pdfmcp/bin/activate
python --version
pip install git+https://github.com/postralai/masquerade@main
python -m masquerade.configure_claude
which pythonpython -c "import masquerade as m; print(f'{m.__path__[0]}/mcp_pdf_redaction.py')"claude_desktop_config.json. Instructions to find the config file are in the image below.{
"mcpServers": {
"pdf-redaction": {
"command": "/path/to/python", // Run `which python`
"args": ["/path/to/mcp_pdf_redaction.py"], // Run `python -c "import masquerade as m; print(f'{m.__path__[0]}/mcp_pdf_redaction.py')"`
"env": {
"TINFOIL_API_KEY": "your_api_key" // Create Tinfoil account and paste API key
}
}
}
}
Note: Don't upload the original PDF to Claude, only the file path.
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.
This project is licensed under the MIT License - see the LICENSE file for details.
For questions and common issues, please see the FAQ section or open an issue on GitHub.
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Minimal Coding Agent Harness on MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read