MCP Server Auditor runs on your own machine — the client starts it, so there is no endpoint to ping. 391 installs a week from npm. Last commit 11 Oct 2026.
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
Today is the operative word: we check MCP Server Auditor 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 mcp-server-auditor -- npx -y @guardbee/mcp-server-auditor
{
"mcpServers": {
"mcp-server-auditor": {
"args": [
"-y",
"@guardbee/mcp-server-auditor"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-server-auditor]
command = "npx"
args = ["-y", "@guardbee/mcp-server-auditor"]
{
"mcpServers": {
"mcp-server-auditor": {
"args": [
"-y",
"@guardbee/mcp-server-auditor"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-server-auditor": {
"args": [
"-y",
"@guardbee/mcp-server-auditor"
],
"command": "npx"
}
}
}
Scans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets
Security scanner for MCP servers - detects tool poisoning and injection
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Security scanner for MCP servers and skills: Unicode injection, patterns, secrets.
Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration)
Security scanner for MCP servers. SSRF, path traversal, injection, auth, secrets. Grade A-F.
Scans MCP servers for tool poisoning, prompt injection and supply chain risks.
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
Answers built from our own checks of this server.