AgentLair

io.github.piiiico/agentlairpiiiicostreamable-httpv1.3.1Scanned 3 hours ago

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.

Reads private data · 6
Reads text others write · 3
Can send data out · 2
No findings

Anlyon alternative

9 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

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 2Removes, cancels or revokes something.Claude 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 2Sends, pays, publishes or merges: once done, it cannot be taken back.Claude 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 5Creates or changes something that can be changed back.Claude 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 6Looks things up and changes nothing.Show 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.; calendar_get_feed
calendar_list_events
list_addresses
read_message
vault_get
vault_list
Reads text others write3: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; calendar_get_feed
list_addresses
read_message
Can send data out2: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.; delegate_task
send_email

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.

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.

All changes to this server

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

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://anlyon.dev/api/v1/servers/io.github.piiiico/agentlair/verify?hash=16a1466ae24df4d0f813270a49cf0e58b11f98872dde63283f4786c180f479b5" | jq -e '.changed == false'

Pinned hash 16a1466ae24d, from Nov 4, 2026, 23:18 UTC.

Watch

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

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

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

Badge

[![anlyon.dev](https://anlyon.dev/badge/io.github.piiiico/agentlair.svg)](https://anlyon.dev/servers/io.github.piiiico/agentlair)

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