AgentGuard by Audiscape
Server Details
Stops runaway AI agent loops and token burn. Checks each tool call before it runs. No signup.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 0.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
audit_domain (live scan) and get_remediation_preview (preview + scorecard URL) both key off a domain and return related scoring artifacts, so an agent could occasionally pick the wrong one. create_checkout_session and guard_check_session are unmistakably distinct, and the description of the guard tool clearly frames its pre-call role.
All four tools follow a clean verb_noun snake_case pattern (audit_domain, create_checkout_session, get_remediation_preview, guard_check_session). Verbs are used meaningfully and consistently across the set.
Four tools is a lean, well-scoped surface for a domain-audit + remediation-upsell flow, and each tool has a clear job. The only wrinkle is that guard_check_session serves a different purpose (agent loop/spend guarding) than the other three.
The audit-to-preview-to-checkout funnel is covered, but there is no tool to retrieve a completed audit result/history, fetch the full remediation plan after purchase, or verify remediation status. The guard tool also has no companion (e.g. reset/inspect session state), leaving dead ends.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
See, price, and control every tool call your AI agents make: policy checks, cost, and audit tools.
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Pay-per-call safety checks for AI agents: screen a crypto address or URL before you transact.
Authorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables autonomous AI agents to operate safely by intercepting risky tool calls, evaluating them against policy, and suspending them for human approval via Slack, Telegram, or a web dashboard.2Apache 2.0
- AlicenseNot gradedqualityBmaintenanceA free, local check before your AI agent acts: every tool action is checked against your YAML rules and returns ACT, BLOCK or ESCALATE with an audit record. Optional: send escalations to Flow for a judgment.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceGates agent tool execution with human approval, audit trails, and replay-resistant permits, enabling safe use of tools in agent loops.MIT
- AlicenseAqualityBmaintenanceEnables AI coding agents to block destructive shell commands before they run, audit code and git diffs for security and quality regressions without spending agent tokens, and route or prune context. Ships a PreToolUse hook firewall and a live local dashboard for watching and overriding every decision per project.9MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.