MCP Server Security Scanner runs on your own machine — the client starts it, so there is no endpoint to ping. 6 installs a week from npm.
Scan MCP configs for 30+ CVEs, prompt injection, tool poisoning; validate OAuth configs
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 mcp-server-security-scanner -- npx -y mcp-server-security-scanner
{
"mcpServers": {
"mcp-server-security-scanner": {
"args": [
"-y",
"mcp-server-security-scanner"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-server-security-scanner]
command = "npx"
args = ["-y", "mcp-server-security-scanner"]
{
"mcpServers": {
"mcp-server-security-scanner": {
"args": [
"-y",
"mcp-server-security-scanner"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-server-security-scanner": {
"args": [
"-y",
"mcp-server-security-scanner"
],
"command": "npx"
}
}
}
Security scanner for MCP servers - detects tool poisoning and injection
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
Security & DLP proxy for MCP: tool-poisoning scans, PII redaction on tool args/results. Beta.
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
Security sidecar for MCP servers: prompt-injection scan, Ed25519 verify, tools/list drift. 10 tools.
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
Scan AI agents for tool-calling vulnerabilities: prompt leaks, hijacking, injections, and more.
Scan for prompt injection, secrets, PII, and vet MCP servers before installation
Answers built from our own checks of this server.