AgentLair
NPM · @AGENTLAIR/MCP · 2 COMPONENTS
Give AI agents a real email address, vault, calendar, and task delegation via MCP.
Available components
Last scanned (21 hours ago)
Scores higher than 75% of npm servers
Category Communication
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 92 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 167 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability82
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 1205 tokens (~80/item across 15 items; 15 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_email" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (16)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Security disclosure
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 +1
- Stability: 0.97 → pass security
- 19 Nov 26 −1
- Stability: pass → 0.97 functional
- 14 Nov 26 +6
- Source repository: unverified → pass ▲ security
- 13 Nov 26 −5
- Provenance: pass → unverified ▼ security
- Stability: 0.97 → pass security
- 11 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Nov 26 −2
- Stability: pass → 0.90 functional
- 4 Nov 26 +1
- Stability: 0.97 → pass security
- 3 Nov 26 −1
- Stability: pass → 0.97 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/@agentlair/mcp@1.3.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 92 packages
| Packages resolved | 92 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
calendar_create_event ~181
Create a calendar event on your AgentLair calendar. Events are published via iCal feed for human subscription (Google Calendar, Apple Calendar, Outlook).
| Name | Type | Req | Description |
|---|---|---|---|
| attendees | array | – | Optional list of attendee email addresses |
| description | string | – | Optional event description / notes |
| end | string | yes | Event end time in ISO 8601 format. Date-only ("2026-03-21") or datetime ("2026-03-20T15:00:00Z") |
| location | string | – | Optional event location (address, URL, or room name) |
| start | string | yes | Event start time in ISO 8601 format. Date-only ("2026-03-20") or datetime ("2026-03-20T14:00:00Z") |
| summary | string | yes | Event title / summary (required) |
No output schema declared.
No examples provided.
calendar_delete_event ~50
Delete an event from your AgentLair calendar by event ID. Use calendar_list_events to find event IDs.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Event ID to delete (e.g. evt_abc123...) |
No output schema declared.
No examples provided.
calendar_get_feed ~48
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
calendar_list_events ~83
List events on your AgentLair calendar. Optionally filter by date range.
| Name | Type | Req | Description |
|---|---|---|---|
| from | string | – | Optional start of date range filter (ISO 8601, e.g. "2026-03-01") |
| to | string | – | Optional end of date range filter (ISO 8601, e.g. "2026-03-31") |
No output schema declared.
No examples provided.
check_inbox ~70
Check the inbox for an @agentlair.dev address. Returns recent messages with sender, subject, and received time.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | The @agentlair.dev address to check |
| limit | number | – | Max messages to return (default: 10, max: 50) |
No output schema declared.
No examples provided.
claim_address ~70
Claim a new @agentlair.dev email address for your agent. No DNS or SMTP setup required. Free tier: up to 3 addresses.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | Full address to claim, e.g. "my-agent@agentlair.dev". Must end in @agentlair.dev. |
No output schema declared.
No examples provided.
delegate_task ~149
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.
| Name | Type | Req | Description |
|---|---|---|---|
| constraints | string | – | Timing constraints, requirements, or limits |
| context | string | – | Background information the agent needs to execute the task |
| priority | string | – | Task priority (default: normal) |
| task | string | yes | What to do — be specific and self-contained. The receiving agent has no context from your conversation. |
| to | string | yes | Target agent's AgentLair email (e.g. pico@agentlair.dev) |
No output schema declared.
No examples provided.
list_addresses ~21
List all @agentlair.dev addresses claimed on your account.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
preflight_trust_check ~109
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.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | AgentLair agent ID to check (format: acc_<alphanumeric>). Found via the agent's AgentLair profile or DID document. |
No output schema declared.
No examples provided.
read_message ~63
Read the full content of a specific email message, including the body. Use message IDs from check_inbox.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | The @agentlair.dev address that received the message |
| message_id | string | yes | Message ID from check_inbox results |
No output schema declared.
No examples provided.
send_email ~135
Send an email from an @agentlair.dev address you own to any recipient. No SMTP setup needed.
| Name | Type | Req | Description |
|---|---|---|---|
| cc | array | – | Optional CC addresses |
| from | string | yes | Sender address — must be a claimed @agentlair.dev address (e.g. my-agent@agentlair.dev) |
| html | string | – | Optional HTML body (supplement to text) |
| in_reply_to | string | – | Message-ID to reply to (for email threading) |
| subject | string | yes | Email subject line |
| text | string | – | Plain text body |
| to | – | yes | Recipient address or array of addresses |
No output schema declared.
No examples provided.
vault_delete ~34
Delete a key and all its versions from the AgentLair Vault.
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | Vault key name to delete |
No output schema declared.
No examples provided.
vault_get ~34
Retrieve a stored value from the AgentLair Vault by key name.
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | Vault key name to retrieve |
No output schema declared.
No examples provided.
vault_list ~26
List all keys stored in your AgentLair Vault (metadata only, values not returned).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
vault_put ~132
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).
| Name | Type | Req | Description |
|---|---|---|---|
| key | string | yes | Vault key name (1-128 chars, alphanumeric + _ - .). Examples: 'openai-key', 'session_token', 'config.json' |
| metadata | object | – | Optional JSON metadata (labels, timestamps, etc.) — never encrypted |
| value | string | yes | Value to store. For secrets: encrypt first, then store the ciphertext. |
No output schema declared.
No examples provided.
How do I install the AgentLair MCP server?
AgentLair runs locally as an npm package, launched with npx -y @agentlair/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @agentlair/mcp
claude mcp add piiiico-agentlair -- npx -y @agentlair/mcp
What is the AgentLair MCP server?
AgentLair is an MCP server listed in the public MCP registry as io.github.piiiico/agentlair. Give AI agents a real email address, vault, calendar, and task delegation via MCP. This page covers its npm package (@agentlair/mcp).
Is the AgentLair MCP server safe to use?
AgentLair scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the AgentLair MCP server expose?
AgentLair exposes 15 tools: claim_address, send_email, check_inbox, read_message, list_addresses, and 10 more. Their descriptions and schemas cost roughly 1,205 tokens of context every time the server is loaded.
Is the AgentLair MCP server still maintained?
AgentLair is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the AgentLair MCP server under?
AgentLair declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the AgentLair MCP server?
VerifyMCP ran 16 checks on AgentLair, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.