ai.aqta/seal
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Verify Seal AI decision receipts: signed evidence anyone can check, no account needed.
| Author | ai.aqta |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 207 ms |
| Last measured | 2026-10-24 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"seal": {
"url": "https://app.aqta.ai/api/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (10)
verify_receiptread-onlyCheck 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.
Parameters:
receipt(required) — ['object', 'string'] — The record, as a JSON object or a JSON string.profile— string — Usually omit this. The record's own signed version tag selects the format, and ATTESTATION-v1 is the default. Pass 'ACTION-v1' only to force an agent-action record to be checked as one.public_key— string — Base64url Ed25519 key to check against. Omit it to check against Seal's published issuer keys; a record carrying any other key then fails. A key you supply is used as given, and issuer_key in the result says whether it is a Seal issuer key.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
decode_receiptread-onlyRead a receipt field by field, with stated limits. Does not check the signature.
Parameters:
receipt(required) — ['object', 'string'] — The receipt, as a JSON object or a JSON string.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
get_public_keyread-onlyFetch the published Seal signing key.
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
get_sample_receiptread-onlyA genuine signed receipt from the sample workspace (demo key), for trying verification.
Parameters:
outcome— string — Pick a sample with this outcome. A BLOCKED receipt was signed without the call reaching the provider.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
get_review_packread-onlyThe published sample evidence pack: fixed review question, bound receipts, disclosure.
Parameters:
pack_id— string — Pack id. Only the published "sample" pack is available without an account.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
verify_evidence_packread-onlyVerify 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.
Parameters:
pack— ['object', 'string'] — A pack object, or "sample" for the published sample pack.public_key— string — Key to check every receipt against. Omit it to check each receipt against Seal's published issuer keys.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
explain_attestation_formatread-onlyThe receipt format: fields, outcomes, verification commands, and what a signature does not establish. Use before describing the format.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
list_my_receiptsread-onlyList your workspace receipts filtered by outcome, policy, model, or date range. Requires your aqta_ key as Bearer.
Parameters:
limit— number — Max rows, default 25.model— string — Only receipts for this model.since— string — ISO timestamp lower bound.until— string — ISO timestamp upper bound.policy— string — Only receipts where this policy ran, e.g. pii_scan.outcome— string — Only receipts with this outcome.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
get_transparency_proofread-onlyInclusion proof plus signed tree head for one of your receipts. Requires your aqta_ key.
Parameters:
attestation_id(required) — string — The attestation_id of one of your receipts.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
workspace_summaryread-onlyOutcome, model and policy counts across your recent receipts. Requires your aqta_ key.
Parameters:
limit— number — How many recent receipts to summarise, default 100.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.