Security & Testing

aqta.ai

This MCP server provides tools for verifying and decoding digital receipts, including checking signatures, retrieving public keys, and accessing sample receipts for testing.

1 endpoint10 known toolsFirst detected August 18, 2026Last detected August 31, 2026

ENDPOINT 1

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

No auth detected

MCP server metadata

Name: seal
Version: 1.1.0

Capabilities

toolspromptsresources

Server instructions

Seal answers what an AI system was allowed to do. ATTESTATION-v1 records a model-call decision; ACTION-v1 records an agent tool action; a refusal is a signed record, not an absence. These tools are read-only: they verify and read records using the published reference verifier, and every record is also checkable offline with npx aqta-verify-receipt. Ground answers in the signed envelopes and verification results, never in stored or dashboard state. When reporting a verdict, include its stated limits: a signature shows fields unchanged, not that the record matches what ran, nor that nothing was omitted.

Known tools 10

verify_receipt

Check that a record still says what was signed: the permitted or refused decision, unchanged, under a trusted or embedded key.

Inferred read-only

decode_receipt

Read a receipt field by field, with stated limits.

Inferred read-only

get_public_key

Fetch the published Seal signing key.

Inferred read-only

get_sample_receipt

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

Inferred read-only

get_review_pack

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

Inferred read-only

verify_evidence_pack

Verify a review pack receipt by receipt.

Inferred read-only

explain_attestation_format

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

Inferred read-only

list_my_receipts

List your workspace receipts filtered by outcome, policy, model, or date range.

Inferred read-only

get_transparency_proof

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

Inferred read-only

workspace_summary

Outcome, model and policy counts across your recent receipts.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.seal]
url = "https://app.aqta.ai/api/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: seal
Remote MCP URL: https://app.aqta.ai/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

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

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "seal",
  "transport": "streamable-http",
  "url": "https://app.aqta.ai/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for aqta.ai was fetched 2026-08-22T02:54:16.826Z.

Trust status Trusted

aqta.ai is assessed as Trusted: Domain runs a meaningful technology spend, consistent with a real business.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.