MCP Watchdog runs on your own machine — the client starts it, so there is no endpoint to ping. 102 installs a week from pypi.
MCP security proxy - detects and blocks 40+ MCP attack classes. Zero config.
Today is the operative word: we check MCP Watchdog 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-watchdog -- uvx mcp-watchdog
{
"mcpServers": {
"mcp-watchdog": {
"command": "uvx",
"args": [
"mcp-watchdog"
]
}
}
}
[mcp_servers.mcp-watchdog]
command = "uvx"
args = ["mcp-watchdog"]
{
"mcpServers": {
"mcp-watchdog": {
"command": "uvx",
"args": [
"mcp-watchdog"
]
}
}
}
{
"servers": {
"mcp-watchdog": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-watchdog"
]
}
}
}
AI security firewall & DLP proxy protecting API keys and blocking destructive commands.
Production security for Node.js apps: investigate live attacks, block IPs, tune detections.
Connects MCP servers, packages, security checks, and release gates in one repo.
Zero-key security toolkit: grade sites A+ to F, check CVE exploits, plain-English attack defenses
Real-time semantic security for AI coding agents and MCP tools
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
Security scanner and runtime proxy for MCP servers.
Answers built from our own checks of this server.