PromptGuard for Grok
co.promptguard/security
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
client:Grok
transport:streamable-http
runtime:npm
tools:13
Install PromptGuard in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"security": {
"type": "http",
"url": "https://api.promptguard.co/mcp"
}
}
}Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs
What Grok can do once it is connected
- promptguard_scan_text
- promptguard_scan_code
- promptguard_redact
- promptguard_status
- promptguard_list_events
- promptguard_get_usage
- promptguard_list_policies
- promptguard_list_audit_log
- promptguard_list_projects
- promptguard_get_fleet_status
- promptguard_list_red_team_tests
- promptguard_list_webhook_deliveries
- promptguard_propose_suppression