PromptGuard runs on your own machine — the client starts it, so there is no endpoint to ping. 60 installs a week from pypi.
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
The linked repository no longer exists on GitHub — it was deleted or made private.
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 -- npx -y @promptguard/mcp-server
{
"mcpServers": {
"security": {
"args": [
"-y",
"@promptguard/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.security]
command = "npx"
args = ["-y", "@promptguard/mcp-server"]
{
"mcpServers": {
"security": {
"args": [
"-y",
"@promptguard/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"security": {
"args": [
"-y",
"@promptguard/mcp-server"
],
"command": "npx"
}
}
}
Answers built from our own checks of this server.