Answers
Answers
Short, direct answers to the questions people ask about controlling what AI agents spend, share and do, each with the commands or code to do it and what it cannot do.
Each page answers one question in its first two sentences, then shows how, then says where the answer stops. They are written to be quoted, by a person or a model. Every page is also Markdown at its address plus .md.
#Spend and payments
- How do I stop an AI agent from spending money without approval?
- How do I control LLM costs per team?
- How do I control what an AI agent pays with x402 or a crypto wallet?
#Approvals and permissions
- How do I make an AI agent ask a person before it acts?
- How do I add approval to tool calls in the OpenAI Agents SDK, LangGraph or the Vercel AI SDK?
- How do I allow or deny MCP tool calls by policy?
- How do I stop an AI agent sending data where it should not?
#Coding agents
- How do I block dangerous commands in Claude Code?
- How do I make Cursor’s agent ask before risky tool calls?
- How do I add Immiscible’s MCP server to Claude Code, Cursor or VS Code?