← all agents · MCP trust index
Authorizes exact autonomous-agent actions against explicit policy, returns short-lived signed receipts, and scans MCP tool metadata for high-risk gaps.
Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:32:10Z, first seen 2026-08-26T06:11:06Z). Not self-submitted, not cached from a directory.
| field | value |
|---|---|
| A2A endpoint | — |
| card source | https://agentpass-protocol.rmalka06.chatgpt.site/.well-known/agent-card.json |
| protocolVersion | — |
| agent version | 0.16.0 |
| preferredTransport | — |
| provider | — |
| skills published | 8 |
| card hash (canonical) | a0cece438c07109b |
| skill | description |
|---|---|
| Budget-capped agent checkout | Choose an IntentFence paid outcome and receive the exact endpoint, validated input, Coinbase Agentic Wallet MCP request, Agentic Wallet argv, proactive x402 MCP tool call, and Base USDC ceiling withou |
| Screen every Base recipient before payment | Run a live Base wallet-risk screen for 0.002 USDC before paying a new recipient, using one budget-capped x402 call and a fail-closed signed result. |
| Self-service production policy pack | Generate a runtime-specific fail-closed TypeScript guard, signed action and policy receipt, negative test vectors, and deployment checklist for 1 USDC through x402. |
| Fail-closed agent action authorization | Bind an exact MCP, HTTP, A2A, or payment action to an allowlist, cost ceiling, retention ceiling, and optional action-specific human approval. Returns a five-minute ES256 receipt and never executes th |
| MCP metadata risk scan | Scan caller-supplied MCP tool definitions for missing schemas, conflicting annotations, absent approval binding, and missing cost boundaries without executing tools. |
| Agent payment preflight | Evaluate caller-declared payment intent and return safe_to_proceed, needs_review, or denied before the caller invokes its downstream tool. IntentFence does not independently authorize or execute the a |
| Live x402 endpoint readiness | Make one bounded credential-free request to a public HTTPS endpoint, block redirects and private-network targets, validate its live x402 challenge, and return a signed receipt without paying the targe |
| Caller-observed x402 quote assessment | Validate and sign the exact PAYMENT-REQUIRED quote observed by the caller against a Base USDC ceiling, explicit payee allowlist, timeout, and resource binding. IntentFence never fetches or pays the ta |
Watching this agent since 2026-08-26T06:11:06Z. Hash = SHA-256 (16 hex)
of the card's canonical JSON (sort_keys, no whitespace), so whitespace-only
edits don't count as drift. Feed:
api/a2a-drift.json.
No drift recorded yet for this agent — its card hash has been stable across every round since we started watching.
Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.
| MCP endpoint | grade | MCP OK | auth |
|---|---|---|---|
| https://agentpass-protocol.rmalka06.chatgpt.site/api/mcp | A | ✓ | open |
Golemreach Trust Layer · A2A index · method & opt-out · card re-fetched every sweep round; opt-out per /trust/bot removes the whole host within 48h.