Agent Security Scanner MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 728 installs a week from npm. Last commit 2 Sep 2026.
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
What the code does
We read the source, 2 h ago · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
<...>/dev/tcp/.../...; sh <&... >&... 2>&
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
postinstall: node scripts/postinstall.js
этот файл ставится пользователю, но в репозитории его нет
full = os.path.normpath(os.path.join(base_dir, candidate))
execFileSync(resolvePythonCommand(), benchArgs, { stdio: 'inherit', timeout: 300000 });
USER root
{"type":"BloomFilter","_size":2597930,"_nbHashes":10,"_filter":{"size":2597936,"content":"b8GuyaJxGxnKF4Ud6mON+ACCWK0UqFPxUnoEwBzxvPprfUQ0iyXL6DuW9v/tPOBElIDxXkCNJPdbw+ZnftXfkIhVv/FNS5sH+d9/l+nnNJxgU6PND+bSgoffcIK8K2pYWVjp/xoXmSv9NHXTouVkvn9rxYMWFZRu5yEqaS0x8PUGQYkve1icBtDfiP2Ykz…
- pattern-regex: (https?:\/\/)?hooks.slack.com\/(services|workflows)\/[A-Za-z0-9+\/]{43,46}
import { existsSync, readFileSync, readdirSync } from 'fs';
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found things in this code
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Agent Security Scanner MCP and you get told the day something new turns up.
Connect this server
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 agent-security-scanner-mcp -- npx -y agent-security-scanner-mcp{
"mcpServers": {
"agent-security-scanner-mcp": {
"args": [
"-y",
"agent-security-scanner-mcp"
],
"command": "npx"
}
}
}[mcp_servers.agent-security-scanner-mcp]
command = "npx"
args = ["-y", "agent-security-scanner-mcp"]{
"mcpServers": {
"agent-security-scanner-mcp": {
"args": [
"-y",
"agent-security-scanner-mcp"
],
"command": "npx"
}
}
}{
"mcpServers": {
"agent-security-scanner-mcp": {
"args": [
"-y",
"agent-security-scanner-mcp"
],
"command": "npx"
}
}
}Alternatives to Agent Security Scanner MCP
same job, measured the same waySecurity gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
AI-powered security scanning using Black Duck Signal for vulnerability detection.
Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.
Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
AI-Powered Security Scanner for LLMs. Detects vulnerabilities and syncs with SynapseAudit.
Agent Security Scanner MCP — questions
Answers built from our own checks of this server.