Security MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 153 installs a week from pypi. Last commit 11 Oct 2026.
Zero-key security toolkit: grade sites A+ to F, check CVE exploits, plain-English attack defenses
Today is the operative word: we check Security MCP 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 security-mcp -- uvx security-mcp
{
"mcpServers": {
"security-mcp": {
"args": [
"security-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.security-mcp]
command = "uvx"
args = ["security-mcp"]
{
"mcpServers": {
"security-mcp": {
"args": [
"security-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"security-mcp": {
"args": [
"security-mcp"
],
"command": "uvx"
}
}
}
Free front-end security check for any website: a grade plus the secrets and keys it exposes.
MCP security proxy - detects and blocks 40+ MCP attack classes. Zero config.
Security grades (A-F) for MCP servers. Check one before you install or trust it. mcpgrade.dev
Plain-English website security check for agents: certificate, headers, scripts, forms, spam.
Free website check: HTTPS setup and security headers, scored with plain-English fixes. No account.
Domain security scanning for AI agents. A-F grades, 8 checks, fix snippets.
Scan a website for vulnerabilities: OWASP Top 10, CVEs, SSL, headers - with plain-English fixes
Plain-English security checks for AI-built apps (Trivy + Opengrep), with fix requests for agents
Answers built from our own checks of this server.