vibe-shield — security scanner for AI-generated code runs on your own machine — the client starts it, so there is no endpoint to ping. 648 installs a week from npm. Last commit 10 Nov 2026.
Scans AI-written code for leaked secrets, unguarded routes and missing RLS.
Today is the operative word: we check vibe-shield — security scanner for AI-generated code 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 vibe-shield -- npx -y @vibefoundry/vibe-shield
{
"mcpServers": {
"vibe-shield": {
"command": "npx",
"args": [
"-y",
"@vibefoundry/vibe-shield"
]
}
}
}
[mcp_servers.vibe-shield]
command = "npx"
args = ["-y", "@vibefoundry/vibe-shield"]
{
"mcpServers": {
"vibe-shield": {
"command": "npx",
"args": [
"-y",
"@vibefoundry/vibe-shield"
]
}
}
}
{
"servers": {
"vibe-shield": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@vibefoundry/vibe-shield"
]
}
}
}
Code security scanner for founders and small teams: leaked secrets, missing RLS, injection, CVEs
Security scanner for AI-written code: SAST, secrets, dependencies, IaC, containers and DAST.
Local-first MCP security scanner and CLI for AI-generated applications.
Security scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization.
Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
Security audit for AI agents — scan code/diffs for leaked secrets, check deps via OSV.
Offline security scanning for AI-generated code: seven open-source scanners in one MCP server.
Audit your MCP servers for poisoned tools and leaked secrets, and check AI-generated code for flaws.
Answers built from our own checks of this server.