Redaction is answering right now. Last checked moments ago. It exposes 2 tools.
Takes the people out of text before a model sees it, and puts them back in the reply.
Nothing serious here today
Today is the operative word: we check Redaction every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.
claude mcp add redaction --transport http https://secureai.one/mcp{
"mcpServers": {
"redaction": {
"url": "https://secureai.one/mcp"
}
}
}[mcp_servers.redaction]
url = "https://secureai.one/mcp"{
"mcpServers": {
"redaction": {
"url": "https://secureai.one/mcp"
}
}
}{
"mcpServers": {
"redaction": {
"url": "https://secureai.one/mcp"
}
}
}Available tools 2
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
redact
restore
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://secureai.one/mcp | streamable-http | answering | 208 ms | 0 min ago |
Alternatives to Redaction
same job, measured the same wayDetect and redact PII, PHI, PCI and secrets in text and files before an AI agent sees them.
A secure, efficient, and intelligent MySQL server for the Model Context Protocol
Audit GitHub repos for malicious and supply-chain code before you depend on them.
Check text for leaked credentials before an agent writes or commits it. Runs locally.
Check the trust/security score of MCP servers, agents, skills & CLIs before you install them.
A secret store for AI agents: the agent never sees the plaintext.
Add a cookie consent banner that blocks trackers before consent and records proof of consent.
MCP security firewall: vet tool definitions before they reach the model.
Redaction — questions
Answers built from our own checks of this server.