Takes the people out of text before a model sees it, and puts them back in the reply.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 2 tools
redact and restore are clear inverses with no overlap. An agent can easily determine when to sanitize text and when to reverse the process.
Both tool names are single, imperative verbs that directly describe their action. The naming convention is consistent and immediately understandable.
Two tools is the minimal complete set for this narrow purpose: one to redact and one to restore. There is no unnecessary bloat or redundancy.
The redaction workflow is fully covered: redact text and restore it using the returned map. No obvious operations are missing for the stated domain.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
redactrestoreRedact names, IDs, emails, phones and card numbers before they reach the model; restore them after.
Detect and redact PII and secrets before text reaches an LLM, with reversible placeholders.
Find and redact leaked secrets, wallet keys and PII before an AI agent sends text.
Detects and redacts PII (emails, phones, SSNs, names, addresses) from text. $0.02/call via x402.
Add one secure layer between your agents and this server.