Strac MCP DLP runs on your own machine — the client starts it, so there is no endpoint to ping. 90 installs a week from pypi. Last commit 4 Sep 2026.
Detect and redact PII, PHI, PCI and secrets in text and files before an AI agent sees them.
Today is the operative word: we check Strac MCP DLP 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 strac-mcp-dlp -e 'STRAC_API_KEY=<STRAC_API_KEY>' -- uvx strac-mcp-dlp
{
"mcpServers": {
"strac-mcp-dlp": {
"command": "uvx",
"args": [
"strac-mcp-dlp"
],
"env": {
"STRAC_API_KEY": "<STRAC_API_KEY>"
}
}
}
}
[mcp_servers.strac-mcp-dlp]
command = "uvx"
args = ["strac-mcp-dlp"]
env = { STRAC_API_KEY = "<STRAC_API_KEY>" }
{
"mcpServers": {
"strac-mcp-dlp": {
"command": "uvx",
"args": [
"strac-mcp-dlp"
],
"env": {
"STRAC_API_KEY": "<STRAC_API_KEY>"
}
}
}
}
{
"servers": {
"strac-mcp-dlp": {
"type": "stdio",
"command": "uvx",
"args": [
"strac-mcp-dlp"
],
"env": {
"STRAC_API_KEY": "<STRAC_API_KEY>"
}
}
}
}
Put your own value in place of
<STRAC_API_KEY> (Strac API key. Request one at https://www.strac.io/mcp-integrations. Keys are prefixed sk_live_ (production) or sk_test_ (sandbox)).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
STRAC_API_BASE (Override the Strac API base URL. Defaults to https://api.live.tokenidvault.com for sk_live_ keys and https://api.test.tokenidvault.com for sk_test_ keys), STRAC_API_TIMEOUT (Request timeout in seconds. Defaults to 60).
Find and redact leaked secrets, wallet keys and PII before an AI agent sends text.
Detect and redact PII and secrets (API keys, tokens) in text, HTML or PDF before it reaches an LLM.
Find and redact personal data and secrets in text before it reaches a model. Local, no account.
Offline secret scanning for AI agents. Redacted findings; scans text and files in a chosen root.
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
A secret store for AI agents: the agent never sees the plaintext.
Deterministic no-LLM MCP server that scrubs secrets before they reach an agent. Never leaks values.
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
Answers built from our own checks of this server.