Skip to content

AgentLair MCP server

io.github.piiiico/agentlairpiiiicostreamable-httpv1.3.1Scanned

Give AI agents a real email address, vault, calendar, and task delegation via MCP.

15 tools: 2 can delete or cancel things, 2 do something that can't be undone, 5 change things and 6 only read.

Tools: 2 delete, 2 irreversible, 5 write, 6 read.
  • Reads private data · 6
  • Reads text others write · 3
  • Can send data out · 2
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here can delete or cancel things and 2 do something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 AgentLair MCP server can do

The AgentLair MCP server is published by the GitHub account piiiico. It has 15 tools. It can delete or cancel things (2 tools: vault_delete and calendar_delete_event), do things that cannot be undone, such as sending, paying or publishing (send_email and delegate_task) and create or change data (5 tools: check_inbox, claim_address, preflight_trust_check, vault_put and 1 more). 6 tools only read.

6 tools read private data (read_message, list_addresses, vault_get and 3 more); 3 tools bring in text other people can write (read_message, list_addresses and calendar_get_feed); 2 tools can send data out of your system (send_email and delegate_task). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

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 18, 2026, version 1.3.1.

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.

15 tools

Deletes or cancels 2Claude Code: deny
  • calendar_delete_eventDelete an event from your AgentLair calendar by event ID.No findings

    Why it is in this group

    • The name "calendar_delete_event" says "delete": a word for removing or ending something.
    Description, as the server wrote it
    Delete an event from your AgentLair calendar by event ID. Use calendar_list_events to find event IDs.
  • vault_deleteDelete a key and all its versions from the AgentLair Vault.No findings

    Why it is in this group

    • The name "vault_delete" says "delete": a word for removing or ending something.
    Description, as the server wrote it
    Delete a key and all its versions from the AgentLair Vault.
Can't be undone 2Claude Code: ask
  • delegate_taskDelegate a task to another AgentLair agent.Can send data outNo findings

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Delegate a task to another AgentLair agent. The task is delivered to the agent's inbox and picked up asynchronously. Use this when you need another agent to do something — send an email, run a deployment, do research, etc.
  • send_emailSend an email from your AgentLair address (@agentlair.dev) to any recipient.Can send data outNo findings

    Why it is in this group

    • The name "send_email" says "send": a word for sending, and what is sent cannot be taken back.
    • The input addresses people (input.to): what it sends cannot be taken back.

    What it can reach

    • outboundThe name "send_email" says "send": it sends or publishes something to other people.
    • outboundThe input takes a destination (input.to): what the tool writes goes there.
    Description, as the server wrote it
    Send an email from your AgentLair address (@agentlair.dev) to any recipient. No SMTP or DNS setup needed.
Changes things 5Claude Code: ask
  • calendar_create_eventCreate a calendar event on your AgentLair calendar.No findings

    Why it is in this group

    • The name "calendar_create_event" says "create": a word for a change.
    Description, as the server wrote it
    Create a calendar event on your AgentLair calendar. Events are published via iCal feed for human subscription (Google Calendar, Apple Calendar, Outlook).
  • check_inboxCheck the inbox for an @agentlair.dev email address.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
    Check the inbox for an @agentlair.dev email address. Returns recent messages with sender, subject, and received time.
  • claim_addressClaim a new @agentlair.dev email address for your agent.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
    Claim a new @agentlair.dev email address for your agent. Free tier supports multiple addresses.
  • preflight_trust_checkCheck trust readiness before engaging with an agent.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
    Check trust readiness before engaging with an agent. Returns a ReadinessCard: trust score, behavioral maturity level, whether it's safe to engage, and any caveats. Call this before delegating tasks, accepting agent output, or authorizing payments involving an unknown agent. Free — no extra charge beyond your API key.
  • vault_putStore a value in the AgentLair Vault.No findings

    Why it is in this group

    • The name "vault_put" says "put": a word for a change.
    Description, as the server wrote it
    Store a value in the AgentLair Vault. Use this to persist API keys, secrets, or any data your agent needs across sessions. Best practice: encrypt sensitive data client-side before storing (the server stores whatever you send).
Only reads 6Show 6 read-only tools
  • calendar_get_feedGet the public iCal subscription URL for your AgentLair calendar.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "calendar_get_feed" says "get": a word for reading.

    What it can reach

    • private-dataThe name "calendar_get_feed" says "get" and "calendar": it reads calendars.
    • private-dataThe description's first sentence says "get" and "calendar": it reads calendars.
    • untrusted-inputThe description's first sentence says "get" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Get the public iCal subscription URL for your AgentLair calendar. Share this URL with calendar apps (Google Calendar, Apple Calendar, Outlook) so humans can subscribe and see agent-created events.
  • calendar_list_eventsList events on your AgentLair calendar.Reads private dataNo findings

    Why it is in this group

    • The name "calendar_list_events" says "list": a word for reading.

    What it can reach

    • private-dataThe name "calendar_list_events" says "list" and "calendar": it reads calendars.
    • private-dataThe description's first sentence says "list" and "calendar": it reads calendars.
    Description, as the server wrote it
    List events on your AgentLair calendar. Optionally filter by date range.
  • list_addressesList all @agentlair.dev email addresses associated with your API key.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_addresses" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "email": it reads mail.
    • untrusted-inputThe description's first sentence says "list" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    List all @agentlair.dev email addresses associated with your API key.
  • read_messageRead the full content of a specific email message, including the body text.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "read_message" says "read": a word for reading.

    What it can reach

    • private-dataThe name "read_message" says "read" and "message": it reads messages.
    • private-dataThe description's first sentence says "read" and "email": it reads mail.
    • untrusted-inputThe name "read_message" says "read" and "message": it reads messages, which other people can write.
    • untrusted-inputThe description's first sentence says "read" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Read the full content of a specific email message, including the body text.
  • vault_getRetrieve a stored value from the AgentLair Vault by key name.Reads private dataNo findings

    Why it is in this group

    • The name "vault_get" says "get": a word for reading.

    What it can reach

    • private-dataThe name "vault_get" says "get" and "vault": it reads secrets.
    • private-dataThe description's first sentence says "retrieve" and "vault": it reads secrets.
    Description, as the server wrote it
    Retrieve a stored value from the AgentLair Vault by key name.
  • vault_listList all keys stored in your AgentLair Vault (metadata only, values not returned).Reads private dataNo findings

    Why it is in this group

    • The name "vault_list" says "list": a word for reading.

    What it can reach

    • private-dataThe name "vault_list" says "list" and "vault": it reads secrets.
    • private-dataThe description's first sentence says "list" and "vault": it reads secrets.
    Description, as the server wrote it
    List all keys stored in your AgentLair Vault (metadata only, values not returned).

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.

36 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.

Reads private data6
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write3
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__agentlair__delegate_task",
      "mcp__agentlair__send_email"
    ]
  }
}

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.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:23 UTC, unchanged since Nov 5, 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
9
Protocol version
2025-03-26
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 9 tools that change things (2 destructive, 2 irreversible, 5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agentlair-mcp-server.amdal-dev.workers.dev/mcp: tools/list returned 15 tools to an anonymous client, including vault_delete (destructive), calendar_delete_event (destructive), send_email (irreversible), delegate_task (irreversible), check_inbox (write) and 4 more

    What this check looks for

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 1.3.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http agentlair https://agentlair-mcp-server.amdal-dev.workers.dev/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http agentlair https://agentlair-mcp-server.amdal-dev.workers.dev/mcp --header 'Authorization: <your-authorization>'

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agentlair__read_message",
      "mcp__agentlair__list_addresses",
      "mcp__agentlair__vault_get",
      "mcp__agentlair__vault_list",
      "mcp__agentlair__calendar_list_events",
      "mcp__agentlair__calendar_get_feed"
    ],
    "ask": [
      "mcp__agentlair__send_email",
      "mcp__agentlair__check_inbox",
      "mcp__agentlair__claim_address",
      "mcp__agentlair__preflight_trust_check",
      "mcp__agentlair__vault_put",
      "mcp__agentlair__calendar_create_event",
      "mcp__agentlair__delegate_task"
    ],
    "deny": [
      "mcp__agentlair__vault_delete",
      "mcp__agentlair__calendar_delete_event"
    ]
  }
}

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 agentlair. Review it before you use it.

Capability tags behind 8 rules
  • mcp__agentlair__send_email outbound
  • mcp__agentlair__read_message private-data, untrusted-input
  • mcp__agentlair__list_addresses private-data, untrusted-input
  • mcp__agentlair__vault_get private-data
  • mcp__agentlair__vault_list private-data
  • mcp__agentlair__calendar_list_events private-data
  • mcp__agentlair__calendar_get_feed private-data, untrusted-input
  • mcp__agentlair__delegate_task outbound

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/io.github.piiiico/agentlair/verify?hash=16a1466ae24df4d0f813270a49cf0e58b11f98872dde63283f4786c180f479b5" | jq -e '.changed == false'

Pinned hash 16a1466ae24d, from Nov 18, 2026, 17:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.piiiico/agentlair/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.piiiico/agentlair
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.piiiico/agentlair.svg)](https://radar.anlyon.com/servers/io.github.piiiico/agentlair)

Source: MCP Registry · repository. Synced Nov 4, 2026, 23:18 UTC.

AgentLair MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the AgentLair MCP server safe?

No scan can promise that. What its definitions show: 15 tools, 9 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 AgentLair MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: vault_delete and calendar_delete_event.

Can the AgentLair MCP server do things that cannot be undone?

Yes. 2 tools can send, pay, publish or merge: send_email and delegate_task.

What tools does the AgentLair MCP server have?

15 tools: 2 destructive, 2 irreversible, 5 write, 6 read. vault_delete, calendar_delete_event, send_email, delegate_task, check_inbox, claim_address, preflight_trust_check, vault_put and 7 more.

Does the AgentLair MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the AgentLair MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_email and delegate_task.

Has the AgentLair MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 18, 2026.