Aegis

Last 30 days

Uptime

100%

Response time

1.4 s typical, 1.6 s slowest 5%

Last check

9 h ago

Next check

any minute now

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "aegis": {
      "type": "http",
      "url": "https://aegis-mcp.borisinc.com/mcp"
    }
  }
}

8 tools

• discover

  Search the Aegis registry of agent-payable services, ranked by verification-backed trust. Free.

• check_before_pay

  FREE preflight BEFORE you pay: should you pay THIS endpoint? Stored verification signals only (no probe, no spend) - registered?, payment-worthiness, confidence, coverage, reasons, evidence. The top of the funnel for the paid trust_check, which adds the fresh probe pass + ERC-800

• smart_discover

  Describe what you need in plain language; Aegis maps it to the best verified services (LLM intent matching). Paid $0.01 via x402.

• trust_check

  Paid-delivery-verified trust verdict BEFORE you pay: score, tier, recommendation, and explainable confidence+reasons+evidence (Aegis pays real money to confirm delivery; coverage-only scores cannot). Paid $0.05 via x402 (_meta['x402/payment']).

• erc8004_reputation

  On-chain ERC-8004 reputation for any registered agent (Base IdentityRegistry) + Aegis probe cross-check + divergence flag. Paid $0.005 via x402 (_meta['x402/payment']).

• route_batch

  Pay ONCE, Aegis fulfills MANY verified services with per-item failover. items=[{url|capability, params?}]. Charged only if all deliver. Dynamic x402 via _meta.

• route

  Pay THROUGH Aegis: we buy the best verified service for you (by url or capability) and relay the data, failing over if one is down. One integration reaches the whole registry; not charged if nothing delivers. Dynamic x402 price via _meta.

• procure

  TASK+BUDGET procurement: describe what you need in plain language + max spend; Aegis picks the best verified service, executes with failover, captures only on delivery, returns data + Ed25519-signed receipt. Never over budget. Dynamic x402 via _meta.

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks