MCP Secret Scrub runs on your own machine — the client starts it, so there is no endpoint to ping. 97 installs a week from pypi. Last commit 28 Aug 2026.
Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.
Today is the operative word: we check MCP Secret Scrub every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-secret-scrub -- uvx mcp-secret-scrub
{
"mcpServers": {
"mcp-secret-scrub": {
"args": [
"mcp-secret-scrub"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp-secret-scrub]
command = "uvx"
args = ["mcp-secret-scrub"]
{
"mcpServers": {
"mcp-secret-scrub": {
"args": [
"mcp-secret-scrub"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp-secret-scrub": {
"args": [
"mcp-secret-scrub"
],
"command": "uvx"
}
}
}
Local MCP tools for secret status and guarded deployment. Values never reach the agent.
Deterministic, no-LLM security scanner for MCP servers, plus an inline proxy gate.
Detect and redact PII, PHI, PCI and secrets in text and files before an AI agent sees them.
AI agents use your Obsidian secrets by name — values never reach their context.
Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.
Detect and redact PII and secrets before text reaches an LLM, with reversible placeholders.
Detect hardcoded secrets in source and config. Reports masked previews, never the values.
A secure MCP server that lets AI agents query databases safely.
Answers built from our own checks of this server.