Grade B
xyz.getava/ava
xyz.getava/ava · v0.5.1 · 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
Coding agents run multi-leg cross-chain DeFi. Legs re-derived from your sentence before signing.
Source: https://github.com/kamalbuilds/ava-4.0
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 15 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 3 tool(s) can execute commands or delete data (ava_approve_execute, ava_lend_execute, ava_eval_mandate). Require confirmation before the agent calls them. |
What was checked
- https://api.getava.xyz/mcp: answers without auth
Public tools: ava_copilot_turn, ava_approve_execute, ava_lend_execute, ava_portfolio, ava_session, ava_create_agent, ava_provision_wallet, ava_preview_tx, ava_plan_workflow, ava_plan_standing, ava_create_mandate, ava_list_mandates, ava_eval_mandate, ava_agent_record, ava_get_receipt
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/xyz-getava-ava-3daf4e05)