78trust / 100

Seal

by app.aqta.ai in Security & trust

MCP serverPassing, checked 3 h ago

Verify Seal AI decision receipts: signed evidence anyone can check, no account needed.

https://app.aqta.ai/api/mcp

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
305 ms typical, 336 ms slowest 5%
Last check
3 h ago
Next check
in 3 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "seal": {
      "type": "http",
      "url": "https://app.aqta.ai/api/mcp"
    }
  }
}

10 tools

  • verify_receipt

    Check that a record still says what was signed: the permitted or refused decision, unchanged, under Seal's published issuer keys or a key you supply. Handles both formats: ATTESTATION-v1 (a model-call decision) and ACTION-v1 (an agent tool action). No Aqta service in the check.

  • decode_receipt

    Read a receipt field by field, with stated limits. Does not check the signature.

  • get_public_key

    Fetch the published Seal signing key.

  • get_sample_receipt

    A genuine signed receipt from the sample workspace (demo key), for trying verification.

  • get_review_pack

    The published sample evidence pack: fixed review question, bound receipts, disclosure.

  • verify_evidence_pack

    Verify a review pack receipt by receipt. Each verdict comes from the signed envelope itself, never from stored state, and results are per-receipt, never an average.

  • explain_attestation_format

    The receipt format: fields, outcomes, verification commands, and what a signature does not establish. Use before describing the format.

  • list_my_receipts

    List your workspace receipts filtered by outcome, policy, model, or date range. Requires your aqta_ key as Bearer.

  • get_transparency_proof

    Inclusion proof plus signed tree head for one of your receipts. Requires your aqta_ key.

  • workspace_summary

    Outcome, model and policy counts across your recent receipts. Requires your aqta_ key.

Security scan

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

Recent checks

WhenResultHTTPTime
3 h agoPassed200248 ms
11 h agoPassed200297 ms
20 h agoPassed200305 ms
29 h agoPassed200336 ms
38 h agoPassed200305 ms
46 h agoPassed2001.1 s