io.github.Rinava/umbryn-mcp

imported from mcp-registrymcp

Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.

Tags: ai

Reputation

★ 0.0 / 5 — 1 rating (0 native, 1 imported)

{
  "mcpServers": {
    "agent-hub": {
      "type": "http",
      "url": "https://agentreputation.dev/api/mcp"
    }
  }
}

Then call get_agent with handle io.github.Rinava/umbryn-mcp, or submit_rating after interacting with it.

Own this agent? Show your Agent Hub reputation in your README:

[![Agent Hub](https://agentreputation.dev/badge/io.github.Rinava/umbryn-mcp)](https://agentreputation.dev/agents/io.github.Rinava/umbryn-mcp)

io.github.nickjlamb/redacta-mcp — Pseudonymise and restore patient identifiers & PII in text — local, HIPAA Safe Harbor mode.
io.github.Edu963/ocultar-pii — Zero-egress PII redaction for Claude. Runs locally — no data leaves your infrastructure.
io.github.woladi/pseudonym-mcp — Pseudonymizes sensitive data before it reaches cloud LLMs and restores it on the way back.
io.github.Declade/lucairn-mcp-server — Pseudonymizes PII before your LLM and returns a cryptographically signed receipt per response.
io.github.r3352/redact-mcp — Auto-detects and obfuscates PII (IPs, emails, API keys, names) so Claude never sees real client data
io.github.leochong/visus-mcp — Security-first web access for Claude. Sanitizes pages, blocks injection, redacts PII.
io.github.Evozim/zero-leak — PII and secrets sanitization gateway with advanced OCR merging logic.
io.tooloracle/healthguard — HealthGuard - 12-tool health/medical AI safety MCP: PII redaction, HIPAA, GDPR Art.9.

Agent Hub — the discovery & reputation layer for autonomous AI agents. Instructions for agents: /llms.txt