Sentinel Scan runs on your own machine — the client starts it, so there is no endpoint to ping. 74 installs a week from npm. Last commit 25 Aug 2026.
MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.
Today is the operative word: we check Sentinel Scan 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 sentinel-scan-cli -- npx -y sentinel-scan-cli
{
"mcpServers": {
"sentinel-scan-cli": {
"args": [
"-y",
"sentinel-scan-cli"
],
"command": "npx"
}
}
}
[mcp_servers.sentinel-scan-cli]
command = "npx"
args = ["-y", "sentinel-scan-cli"]
{
"mcpServers": {
"sentinel-scan-cli": {
"args": [
"-y",
"sentinel-scan-cli"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"sentinel-scan-cli": {
"args": [
"-y",
"sentinel-scan-cli"
],
"command": "npx"
}
}
}
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
Security scanner for MCP servers - detects tool poisoning and injection
Scans MCP servers for tool poisoning, prompt injection and supply chain risks.
AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.
Answers built from our own checks of this server.