Cofferline
com.cofferline/treasury · 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
Treasury and risk controls for agent wallets: policies, quotes, prediction-market orders.
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 47 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 1 tool(s) can execute commands or delete data (remove_auto_topup). Require confirmation before the agent calls them. |
What was checked
- https://mcp.cofferline.com: answers without auth
Public tools: get_quotes, get_benchmarks, screen_address, list_tokens, list_feedback, submit_feedback, start_siwe_login, complete_siwe_login, get_me, export_account, offboard_account, put_policy, get_policy, check_spend, check_pm_order, poll_events, get_statement, create_intent, get_intent, list_intents, cancel_intent, prepare_delegation, confirm_delegation, renew_delegation, revoke_delegation, get_delegation, list_delegations, panic, get_balance, topup_balance
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/com-cofferline-treasury-9b45d4c8)