Recon Kit MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 106 installs a week from pypi. Last commit 8 Sep 2026.
Read-only network & security recon tools (DNS, TLS, headers, CORS) for AI agents, each graded.
Today is the operative word: we check Recon Kit 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 recon-kit-mcp -- uvx recon-kit-mcp
{
"mcpServers": {
"recon-kit-mcp": {
"command": "uvx",
"args": [
"recon-kit-mcp"
]
}
}
}
[mcp_servers.recon-kit-mcp]
command = "uvx"
args = ["recon-kit-mcp"]
{
"mcpServers": {
"recon-kit-mcp": {
"command": "uvx",
"args": [
"recon-kit-mcp"
]
}
}
}
{
"servers": {
"recon-kit-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"recon-kit-mcp"
]
}
}
}
Read-only MCP access to The Agent Commons: shared security findings for AI agents and their tools.
Domain intelligence for agents: WHOIS, DNS, SSL/TLS, security headers, reputation, subdomains.
Doormat Capital's paid x402 safety tools (token scan, HTTP security headers) for AI agents.
Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.
Network, DNS, mail-auth and MCP endpoint security checks for AI agents, backed by adminkit.net.
Free web tools for AI agents: HTML to Markdown, compliance scan, page profile, security headers.
Real-time semantic security for AI coding agents and MCP tools
Inspects live IPv4/IPv6 DNS resolution, TLS certificate issuer/expiry, and HTTP security grade.
Answers built from our own checks of this server.