Make Audit MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 52 installs a week from npm. Last commit 15 Aug 2026.
Audit Make.com blueprints before importing: hardcoded secrets, dangling refs, risky settings.
Today is the operative word: we check Make Audit MCP 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 make-audit-mcp -- npx -y make-audit-mcp
{
"mcpServers": {
"make-audit-mcp": {
"args": [
"-y",
"make-audit-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.make-audit-mcp]
command = "npx"
args = ["-y", "make-audit-mcp"]
{
"mcpServers": {
"make-audit-mcp": {
"args": [
"-y",
"make-audit-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"make-audit-mcp": {
"args": [
"-y",
"make-audit-mcp"
],
"command": "npx"
}
}
}
Scans code for hardcoded secrets (AWS, Stripe, GitHub, JWTs) before an AI agent commits it.
Detect hardcoded secrets in source and config. Reports masked previews, never the values.
Context-aware secret scanner: lets an AI agent scan, verify, and rewrite secrets before committing.
Security audit for AI agents — scan code/diffs for leaked secrets, check deps via OSV.
Scans AI coding sessions and assistant configs for leaked secrets and risky hooks; local, redacted
Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
Security + bug + perf + refactor audit for Python. Returns 0-10 score + MD report.
Security suite for AI agents: flag drains, permit-phishing & risky actions before signing.
Answers built from our own checks of this server.