MCP Safety Warden runs on your own machine — the client starts it, so there is no endpoint to ping. 3 378 installs a week from pypi. Last commit 28 Oct 2026.
MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
What the code does
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
result = subprocess.run(
…(x,{undo:async()=>{try{await u(f,h,p),await i()}catch(y){o(`Undo failed: ${Ft(y)}`)}}}),!0}catch(x){return o(`Could not update ${g}: ${Ft(x)}`),!1}},[u,i,o]),refresh:i,write:u}}function Qa({open:r,onClose:o,header:i,footer:u,children:c}){return N.useEffect(()=>{if(!r)return;const…
r"|[/\\]\.npmrc(\b|$)"
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
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 mcpsafetywarden -- uvx mcpsafetywarden{
"mcpServers": {
"mcpsafetywarden": {
"command": "uvx",
"args": [
"mcpsafetywarden"
]
}
}
}[mcp_servers.mcpsafetywarden]
command = "uvx"
args = ["mcpsafetywarden"]{
"mcpServers": {
"mcpsafetywarden": {
"command": "uvx",
"args": [
"mcpsafetywarden"
]
}
}
}{
"servers": {
"mcpsafetywarden": {
"type": "stdio",
"command": "uvx",
"args": [
"mcpsafetywarden"
]
}
}
}Alternatives to MCP Safety Warden
same job, measured the same wayAI-driven penetration testing - 22 security tools behind safety-hardened MCP endpoints
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
Local-first MCP proxy with BM25 tool discovery, security scanning, quarantine & ~99% token savings
Scans MCP servers for tool poisoning, prompt injection and supply chain risks.
Guarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools.
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
Security scanner for MCP servers - detects tool poisoning and injection
Real-time semantic security for AI coding agents and MCP tools
MCP Safety Warden — questions
Answers built from our own checks of this server.