Grade B
AgentLair
io.github.piiiico/agentlair · v1.3.1 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Give AI agents a real email address, vault, calendar, and task delegation via MCP.
Source: https://github.com/piiiico/agentlair
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 15 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 2 tool(s) can execute commands or delete data (vault_delete, calendar_delete_event). Require confirmation before the agent calls them. |
What was checked
- https://agentlair-mcp-server.amdal-dev.workers.dev/mcp: answers without auth
- npm: @agentlair/mcp@1.3.0 (static checks only; code not executed)
Public tools: send_email, check_inbox, read_message, list_addresses, claim_address, preflight_trust_check, vault_put, vault_get, vault_list, vault_delete, calendar_create_event, calendar_list_events, calendar_delete_event, calendar_get_feed, delegate_task
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-piiiico-agentlair-6121d3a7)