Categories › AI & Agents › Multi-agent, orchestration & workflows
Stops runaway AI agent loops and token burn. Checks each tool call before it runs. No signup.
Remote server: your requests and data go to agentguard.audiscape.com. Claude Code: claude mcp add --transport http agentguard-by-audiscape https://agentguard.audiscape.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
guard_check_session — Call before each tool call your agent makes. Send the calls so far and the one you are about to make, get back allowed true or false with thaudit_domain — Run a live HTTP audit against a public domain and return score, grade and report URL.get_remediation_preview — Return the remediation preview and scorecard URL for a domain.create_checkout_session — Return a Stripe checkout link for the remediation pack for a domain.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.