Grade B
Agent402.Tools: payments and trust for AI agents
io.github.MikeyPetrillo/agent402 · v0.14.1 · 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
Payment and trust layer for agent commerce (Agentic Finance): pay and verify calls over x402 and MPP
Source: https://github.com/MikeyPetrillo/Agent402
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 16 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (decide.execute). Require confirmation before the agent calls them. |
What was checked
- https://agent402.tools/mcp: answers without auth
- npm: agent402-mcp@0.14.1 (static checks only; code not executed)
Public tools: catalog.search, catalog.find, catalog.call, payment.info, web.search, web.answer, web.news, browser.render, audio.transcribe, memory.read, memory.write, decide.plan, decide.execute, demand.request, server.describe, decide.feedback
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-mikeypetrillo-agent402-50c94a45)