XploitScan runs on your own machine — the client starts it, so there is no endpoint to ping. 163 installs a week from npm.
Security scanner for AI-generated code. 30 free rules; all 223 with a paid-plan API key.
Today is the operative word: we check XploitScan 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 xploitscan-mcp -- npx -y xploitscan-mcp
{
"mcpServers": {
"xploitscan-mcp": {
"command": "npx",
"args": [
"-y",
"xploitscan-mcp"
]
}
}
}
[mcp_servers.xploitscan-mcp]
command = "npx"
args = ["-y", "xploitscan-mcp"]
{
"mcpServers": {
"xploitscan-mcp": {
"command": "npx",
"args": [
"-y",
"xploitscan-mcp"
]
}
}
}
{
"servers": {
"xploitscan-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"xploitscan-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
XPLOITSCAN_API_KEY (Optional. An xpls_ API key from a paid-plan account. Without it, the 30 free rules run; with it, all 223).
Local-first MCP security scanner and CLI for AI-generated applications.
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Offline security scanning for AI-generated code: seven open-source scanners in one MCP server.
Free security scan for AI-written GitHub repos: leaked keys, .env, eval, SQLi, CORS.
Security scan for AI-generated code: injection, SSRF, secrets, weak crypto, unsafe deserialization.
Validates AI-generated Python: syntax, lint, security scan and deterministic repair.
AI visibility for ChatGPT/Perplexity/Claude — triple score (AEO+GEO+Agent) with fix code. Free.
An MCP server for Arcjet - the runtime security platform that ships with your AI code.
Answers built from our own checks of this server.