Security & Testing

secureai.one

An MCP server that redacts personally identifiable information from text with plausible stand-ins and can restore the original text using a returned mapping before data is sent to models or third parties.

1 endpoint2 known toolsFirst detected September 18, 2026Last detected September 18, 2026

ENDPOINT 1

https://secureai.one/mcp

No auth detected

MCP server metadata

Name: secure-ai
Version: 1.0.0

Capabilities

tools

Server instructions

Use redact before sending text that contains personal details to a model or a third party, then restore on the reply. Keep the map redact returns for the life of the conversation — it is not stored here and without it the reply cannot be turned back.

Known tools 2

redact

Replace the people in a piece of text — names, emails, phone numbers, addresses, card and account numbers — with plausible stand-ins, before the text is sent to a model or a third party.

Inferred read-only

restore

Reverse a redaction using the map it returned.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.secure-ai]
url = "https://secureai.one/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "secure-ai": {
      "type": "http",
      "url": "https://secureai.one/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: secure-ai
Remote MCP URL: https://secureai.one/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "secure-ai": {
      "url": "https://secureai.one/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "secure-ai": {
      "type": "http",
      "url": "https://secureai.one/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "secure-ai",
  "transport": "streamable-http",
  "url": "https://secureai.one/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.