sh.agentcard/agentcard
sh.agentcard/agentcard · v1.0.0 · 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
Prepaid virtual cards for AI agents: one-time cards, spend caps, human approvals.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 55 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 2 tool(s) can execute commands or delete data (delete_preset, remove_added_card). Require confirmation before the agent calls them. |
What was checked
- https://mcp.agentcard.sh/mcp: answers without auth
Public tools: buy, surprise_me, get_instructions, whoami, list_cards, get_card_details, get_card_balance, close_card, create_card, get_card_preset, set_card_preset, allow_card_merchant, list_presets, save_preset, delete_preset, get_wallet_link, list_added_cards, remove_added_card, pause_card, resume_card, update_card_limit, get_rewards, redeem_rewards, recommend_card, name_card, start_support_chat, send_support_message, read_support_chat, list_pending_approvals, approve_request
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/sh-agentcard-agentcard-988be0ac)