PromptGuard for Claude.ai
co.promptguard/security
Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
client:Claude.ai
transport:streamable-http
runtime:npm
tools:13
Install PromptGuard in Claude.ai
Settings → Connectors → Add custom connector
https://api.promptguard.co/mcpClaude on the web takes a remote URL and completes OAuth in the browser. For a packaged server use Claude Desktop or Claude Code instead. Claude.ai docs
What Claude.ai 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