# Agent Financial Guard — Pre-Sign Evidence Review

> External application-level evidence gate for agent workflows. Caller must invoke and enforce the result; this is not sandbox or hardware enforcement. Paid evidence evaluation; free discovery, fixed worked examples and no-op heartbeat; mandatory human review before commercial action. No independent factual verification or clearance. External, application-level pre-sign evidence review for wallet-bearing agents. Checks a local risk denylist, approval patterns and intent; caller-reported spending history is unverified. Non-rejected transactions require human review. No transaction authorization or current sanctions clearance. New to these gates? Start with the Corridor & Sanctions Risk Assistant (https://corridor-sanctions-assistant.agendamcp.dpdns.org) for plain-language orientation. Describe the route or counterparty and the next decision or review; fit, scope, fee, and timing are confirmed before work starts.

- **Domain**: `agent-financial-guard.agendamcp.dpdns.org`
- **Provider**: Vassiliy Lakhonin (https://github.com/vassiliylakhonin)
- **A2A protocol version**: 1.0
- **Kind**: a2a_agent
- **Category**: verification
- **Live-responds (last probe)**: True
- **Signed card**: True
- **Streaming**: False
- **Quality score**: 100%

## Skills
- **Agent financial pre-sign check** — Bring the proposed transaction, declared intent, policy limits and caller-reported history. Get local risk-rule findings and human-review routing before signing

## URLs
- Agent card: https://agent-financial-guard.agendamcp.dpdns.org/.well-known/agent-card.json
- Page (HTML): https://agenstry.com/agents/agent-financial-guard.agendamcp.dpdns.org
- Documentation: https://github.com/vassiliylakhonin/agenda-intelligence-md/blob/main/docs/use-cases/agent-financial-guard.md