Grade B
Web3alert for agents
io.web3alert/agent · v0.1.1 · 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
Decoded on-chain events for AI agents: find triggers, subscribe a webhook, read delivery logs.
Source: https://github.com/web3alert/mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 10 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (remove_subscription). Require confirmation before the agent calls them. |
What was checked
- https://web3alert.io/mcp/agent: answers without auth
Public tools: get_account, find_triggers, get_trigger, list_webhooks, add_webhook, create_subscription, list_subscriptions, set_subscription_state, remove_subscription, get_delivery_log
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-web3alert-agent-1f56c988)