mcpField
T
tracepiishield-mcp

tracepiishield-mcp

Remote
github.com/clauxelSecurity0Updated 23w ago
Repository

About tracepiishield-mcp

tracepiishield-mcp is a hosted remote MCP for scanning and redacting personally identifiable information in LLM traces and tool payloads. It also classifies sensitive fields and provides privacy receipts and audit exports.

Key features

  1. 01PII scanning in traces
  2. 02Tool payload redaction
  3. 03Sensitive-field classification
  4. 04Privacy receipt issuance
  5. 05Trace audit exports

Use cases

  1. 01Scanning LLM traces for PII
  2. 02Redacting payloads before review
  3. 03Classifying sensitive fields
  4. 04Exporting trace audit records

MCP support

Exposes privacy and audit tools to MCP clients through a Streamable HTTP remote endpoint. Production requests require a bearer token.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://tracepiishield.clauxel.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://tracepiishield.clauxel.com/mcpAuth required

Tools

Details

From the project README

TracePII Shield MCP

Redact PII from LLM traces and tool payloads before they leave review.

Paid remote MCP for LLM trace PII scanning, payload redaction, sensitive field classification, privacy receipts, and trace audit exports.

Public Endpoints

Access

This is a paid hosted remote MCP. Production calls require a bearer token issued from the product website.

Authorization: Bearer <token>

Unauthenticated browser visits to /mcp return a clear JSON error instead of internal details.

Tools

  • scan_trace_pii
  • redact_tool_payload
  • classify_sensitive_field
  • issue_pii_receipt
  • export_trace_audit

Quick Start

  1. Open the website and choose a plan.
  2. Create or request an API token.
  3. Add the endpoint to an MCP client that supports Streamable HTTP remote servers.
  4. Send JSON-RPC requests with the bearer token.

Useful Links

Status

This repository is a public documentation and directory-submission reference for the hosted service. It does not contain the private production source code.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.