seal MCP server
ai.aqta/sealaqta.aistreamable-httpv1.0.0Scanned
Verify Seal AI decision receipts: signed evidence anyone can check, no account needed.
10 tools: 3 change things and 7 only read.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the seal MCP server can do
The seal MCP server is published by aqta.ai, a domain the MCP Registry verified. It has 10 tools. It can create or change data (3 tools: verify_receipt, verify_evidence_pack and workspace_summary), but cannot delete data. 7 tools only read.
2 tools bring in text other people can write (get_public_key and get_review_pack).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Changes things 3Claude Code: ask
verify_evidence_packVerify a review pack receipt by receipt.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- title: Verify a whole evidence pack
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
verify_receiptCheck 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.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- title: Verify a receipt
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
workspace_summaryOutcome, model and policy counts across your recent receipts.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Outcome, model and policy counts across your recent receipts. Requires your aqta_ key.
Annotations the server declares
- title: Summarise your workspace decisions
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 7Show 7 read-only tools
decode_receiptRead a receipt field by field, with stated limits.No findings
Why it is in this group
- The description's first verb is "read": a word for reading.
Description, as the server wrote it Read a receipt field by field, with stated limits. Does not check the signature.
Annotations the server declares
- title: Read a receipt
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
explain_attestation_formatThe receipt format: fields, outcomes, verification commands, and what a signature does not establish.No findings
Why it is in this group
- The name "explain_attestation_format" says "explain": a word for reading.
Description, as the server wrote it The receipt format: fields, outcomes, verification commands, and what a signature does not establish. Use before describing the format.
Annotations the server declares
- title: Explain the receipt format
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_public_keyFetch the published Seal signing key.Reads text others writeNo findings
Why it is in this group
- The name "get_public_key" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Fetch the published Seal signing key.
Annotations the server declares
- title: Get the published signing key
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
get_review_packThe published sample evidence pack: fixed review question, bound receipts, disclosure.Reads text others writeNo findings
Why it is in this group
- The name "get_review_pack" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_review_pack" says "get" and "review": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "review": it reads comments, which other people can write.
Description, as the server wrote it The published sample evidence pack: fixed review question, bound receipts, disclosure.
Annotations the server declares
- title: Get an evidence pack
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_sample_receiptA genuine signed receipt from the sample workspace (demo key), for trying verification.No findings
Why it is in this group
- The name "get_sample_receipt" says "get": a word for reading.
Description, as the server wrote it A genuine signed receipt from the sample workspace (demo key), for trying verification.
Annotations the server declares
- title: Get a sample receipt
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_transparency_proofInclusion proof plus signed tree head for one of your receipts.No findings
Why it is in this group
- The name "get_transparency_proof" says "get": a word for reading.
Description, as the server wrote it Inclusion proof plus signed tree head for one of your receipts. Requires your aqta_ key.
Annotations the server declares
- title: Prove a receipt is in the log
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_my_receiptsList your workspace receipts filtered by outcome, policy, model, or date range.No findings
Why it is in this group
- The name "list_my_receipts" says "list": a word for reading.
Description, as the server wrote it List your workspace receipts filtered by outcome, policy, model, or date range. Requires your aqta_ key as Bearer.
Annotations the server declares
- title: List your signed receipts
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:24 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://app.aqta.ai/api/mcp: tools/list returned 10 tools to an anonymous client, including verify_receipt (write), verify_evidence_pack (write), workspace_summary (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:decode_receiptOnly readsinputSchema
- Changed:get_transparency_proofOnly readsinputSchema
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http seal https://app.aqta.ai/api/mcpclaude mcp add --transport http seal https://app.aqta.ai/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__seal__decode_receipt",
"mcp__seal__get_public_key",
"mcp__seal__get_sample_receipt",
"mcp__seal__get_review_pack",
"mcp__seal__explain_attestation_format",
"mcp__seal__list_my_receipts",
"mcp__seal__get_transparency_proof"
],
"ask": [
"mcp__seal__verify_receipt",
"mcp__seal__verify_evidence_pack",
"mcp__seal__workspace_summary"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as seal. Review it before you use it.
Capability tags behind 2 rules
- mcp__seal__get_public_key untrusted-input
- mcp__seal__get_review_pack untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.aqta/seal/verify?hash=ad96de83d43f7c0657f2cb183d813f8a5a304b4d9a6db58b8687dc1047b10518" | jq -e '.changed == false'Pinned hash ad96de83d43f, from Nov 11, 2026, 17:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.aqta/seal/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.aqta/seal)Source: MCP Registry. Synced Oct 21, 2026, 17:41 UTC.
seal MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the seal MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the seal MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the seal MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the seal MCP server have?
- 10 tools: 3 write, 7 read. verify_receipt, verify_evidence_pack, workspace_summary, decode_receipt, get_public_key, get_sample_receipt, get_review_pack, explain_attestation_format and 2 more.
Does the seal MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the seal MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the seal MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Oct 30, 2026. Every change is on this page and in its Atom feed.