AIS Agent Flight Recorder — dead-man alerts & resume for AI agents MCP server
ai.aislabs/recorderaislabs.aistreamable-httpv0.1.0Scanned
Dead-man switch for AI agents & cron jobs: heartbeat with state capsule, alerts + resume links
5 tools: 1 can delete or cancel things, 2 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- 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 AIS Agent Flight Recorder — dead-man alerts & resume for AI agents MCP server can do
The AIS Agent Flight Recorder — dead-man alerts & resume for AI agents MCP server is published by aislabs.ai, a domain the MCP Registry verified. It has 5 tools. It can delete or cancel things (1 tool: delete_monitor) and create or change data (2 tools: register_monitor and heartbeat). 2 tools only read.
1 tool reads private data (fetch_capsule).
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.
Last scanned Nov 17, 2026, version 0.1.0.
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.
5 tools
Deletes or cancels 1Claude Code: deny
delete_monitorAgent Flight Recorder — remove a monitor (needs its secret or the owning key).No findings
Why it is in this group
- The name "delete_monitor" says "delete": a word for removing or ending something.
Description, as the server wrote it Agent Flight Recorder — remove a monitor (needs its secret or the owning key).
Changes things 2Claude Code: ask
heartbeatAgent Flight Recorder — "still alive" ping for a registered monitor.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.
Description, as the server wrote it Agent Flight Recorder — "still alive" ping for a registered monitor. Include capsule (any JSON ≤32KB: current step, done, next, ids) so a dead-man alert can carry resume state (stored on the key tier). status:"fail" reports a failure immediately.
register_monitorAgent Flight Recorder — FREE (1 monitor per alert target) / Gateway key (20 monitors + stored capsules + fleet view).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.
Description, as the server wrote it Agent Flight Recorder — FREE (1 monitor per alert target) / Gateway key (20 monitors + stored capsules + fleet view). Register an agent or scheduled job to be watched: you get a monitor_id + secret; the agent then calls heartbeat every period_minutes. If heartbeats stop for period + grace, the alert target (Discord/HTTPS webhook and/or email) is notified with the last state capsule and a resume link.
Only reads 2Show 2 read-only tools
fetch_capsuleAgent Flight Recorder (Gateway key) — get the last state capsule a monitored agent sent, to resume from where it died.Reads private dataNo findings
Why it is in this group
- The name "fetch_capsule" says "fetch": a word for reading.
What it can reach
- private-dataThe input names a secret (input.secret), and the tool reads: it reads secrets.
Description, as the server wrote it Agent Flight Recorder (Gateway key) — get the last state capsule a monitored agent sent, to resume from where it died.
fleet_statusAgent Flight Recorder (Gateway key) — every monitor you own: alive / late / dead, last heartbeat, capsule preview.No findings
Why it is in this group
- The name "fleet_status" says "status": a word for reading.
Description, as the server wrote it Agent Flight Recorder (Gateway key) — every monitor you own: alive / late / dead, last heartbeat, capsule preview.
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 untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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, 19:21 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
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (1 destructive, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.aislabs.ai/recorder/mcp: tools/list returned 5 tools to an anonymous client, including delete_monitor (destructive), register_monitor (write), heartbeat (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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http recorder https://api.aislabs.ai/recorder/mcpclaude mcp add --transport http recorder https://api.aislabs.ai/recorder/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__recorder__fetch_capsule",
"mcp__recorder__fleet_status"
],
"ask": [
"mcp__recorder__register_monitor",
"mcp__recorder__heartbeat"
],
"deny": [
"mcp__recorder__delete_monitor"
]
}
}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 recorder. Review it before you use it.
Capability tags behind 1 rule
- mcp__recorder__fetch_capsule private-data
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.aislabs/recorder/verify?hash=b5988950db7b67831b152c790b488fa75f6d1e359e1b22b0d6391b20f64d9f14" | jq -e '.changed == false'Pinned hash b5988950db7b, from Nov 17, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.aislabs/recorder/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.aislabs/recorder)Source: MCP Registry. Synced Oct 21, 2026, 17:41 UTC.
AIS Agent Flight Recorder — dead-man alerts & resume for AI agents MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AIS Agent Flight Recorder — dead-man alerts & resume for AI agents MCP server safe?
- No scan can promise that. What its definitions show: 5 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 AIS Agent Flight Recorder — dead-man alerts & resume for AI agents MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: delete_monitor.
Can the AIS Agent Flight Recorder — dead-man alerts & resume for AI agents 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 AIS Agent Flight Recorder — dead-man alerts & resume for AI agents MCP server have?
- 5 tools: 1 destructive, 2 write, 2 read. delete_monitor, register_monitor, heartbeat, fetch_capsule and fleet_status.
Does the AIS Agent Flight Recorder — dead-man alerts & resume for AI agents MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AIS Agent Flight Recorder — dead-man alerts & resume for AI agents MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AIS Agent Flight Recorder — dead-man alerts & resume for AI agents MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.