FortFi Treasury MCP
io.github.rebelArtists/fortfi-treasury-mcp · 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
Policy-gated MCP treasury for AI agents — x402 subscribe, 50+ tools, multi-chain.
Source: https://github.com/rebelArtists/fortfi
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 148 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 3 tool(s) can execute commands or delete data (remove_recipient, remove_cosigner, remove_backup_governance_wallet). Require confirmation before the agent calls them. |
What was checked
- https://fortfiapp.com/api/mcp: answers without auth
Public tools: get_mcp_guide, get_treasury_context, list_wallets, list_recipients, list_audit_log, list_activity_report, get_fusion_order_status, get_policy_limits, get_usage_balance, resend_claim_link, list_funding_wallet_agents, list_cosigner_memberships, get_cosigner_rules, update_cosigner_rules, list_pending_cosigner_approvals, add_recipient, remove_recipient, approve_recipient, validate_recipient_manifest, propose_recipient_manifest, validate_payout_manifest, propose_payout_manifest, propose_transfer, invite_agent_cosigner, invite_cosigner, approve_cosigner_action, reject_cosigner_action, get_portfolio, get_account_holdings, review_portfolio
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-rebelartists-fortfi-treasury-mcp-cfdd5300)