The safety layer between your AI agent and the real world. OAuth authentication, risk scoring on every action, tamper-proof audit trails, and an emergency kill switch. Because autonomous agents need guardrails, not just tools.
AI agents are getting autonomous. They schedule tasks, make API calls, move money, interact with external services. But most agent frameworks have zero safety infrastructure. No authentication. No risk assessment before action. No audit trail. No kill switch.
AgentGuard fills that gap. It sits between your agent's decision and the execution — checking identity, scoring risk, logging everything, and stopping dangerous actions before they happen.
Know Your Agent — identity verification before any tool access. OAuth2 flow with scoped permissions.
78 risk scores. Every action evaluated before execution. High-risk actions require human approval.
SHA-256 chain-linked audit trail. Every decision, every tool call, every result — signed and verifiable.
Immediate agent termination. Irreversible. All pending actions cancelled. Full incident log preserved.
Post-execution content analysis. Detect PII leaks, hallucinated data, policy violations in agent outputs.
Verify MCP server integrity before connection. Check signatures, versions, known vulnerabilities.
| Capability | Typical Agent | With AgentGuard |
|---|---|---|
| Authentication | None — any agent connects | OAuth + KYA identity |
| Pre-action check | None — execute blindly | 78 risk scores evaluated |
| Audit trail | Basic logs at best | SHA-256 chain-linked, signed |
| Kill switch | Kill the process manually | Instant state → killed |
| Output scanning | Trust the output | PII/policy violation detection |
| Human-in-the-loop | All or nothing | approval_required state for high-risk |
// Claude Desktop / Cursor
{
"mcpServers": {
"agentguard": {
"url": "https://tooloracle.io/agentguard/mcp/"
}
}
}
// Autonomous agent stack (recommended)
SchedulerOracle → AgentGuard → Preflight → Tools → MemoryOracle
↓ ↓ ↓ ↓ ↓
Cron tasks Auth + Risk Budget Execute Remember
AgentGuard works standalone or as part of the full ToolOracle autonomous agent pipeline: SchedulerOracle schedules tasks, AgentGuard gates execution, Decision Preflight checks budgets, tools execute, and MemoryOracle persists context across sessions.
20 safety tools. x402 USDC micropayments. Open source on GitHub.
GitHub → Trust & Safety servers All 65 servers