AI Agents & MCP Tools
- Can I see what my agent has been doing?
- What security controls can I set on my agent?
- Can my agent transact on another user’s behalf (approvals)?
- How are large transactions handled?
- What automatic abuse protections are there?
- What limits and safeguards apply to my agent?
- Which actions require KYC?
- What are “scopes” and why do they matter?
- How do I connect my AI agent?
- What is the Agents / MCP integration?