Answers
Frequently asked questions.
Questions about agent balances, resources, payment routes and implementation boundaries.
- What is an agent wallet?
- An agent wallet associates allocated balances and resources with an agent and its principal. Cards, communications and USDC signing require their own configured providers; creation is not a guarantee of atomic resource provisioning.
- Who is AgentWallet for?
- Companies that run autonomous AI agents in production — coding agents, ops agents, support agents, media-buying agents, treasury agents, concierge agents, recruiting agents — and the developers building those agent products. If your agent needs to spend, receive, settle or be audited, you need an agent wallet.
- How is AgentWallet different from a normal corporate card?
- AgentWallet associates allocated balances, ownership and supported activity records with individual agents. Optional cards, USDC signing and communication resources depend on account and provider configuration; they are not guaranteed for every agent.
- How do I give my AI agent a credit card?
- Create an agent, then provision eligible card resources through the configured provider flow. Card policy controls and tokenization are available on supported paths; raw-card reveal paths require separate access controls.
- Can AI agents have their own bank account?
- AgentWallet supports allocated fiat balances and configured USDC signing integrations. Resource and payment availability depends on account eligibility, provider configuration and the selected route.
- How do I give my AI agent USDC?
- USDC signing uses CDP when configured; code also includes a sealed-local-key development/test fallback. x402 network support depends on the configured route; verify Base or Base Sepolia configuration before use.
- How do AI agents pay for things?
- The per-agent MCP endpoint advertises tools according to current permissions and configuration. Payment authorization, execution and activity records vary by tool and route.
- How do I limit how much money my AI agent spends?
- Supported spend-gated routes check per-transaction, daily and monthly caps and can require approval. Generic x402.pay_url has an optional per-call maximum, not the mandate-bound spend gate.
- Is it safe to give an AI agent a credit card?
- Card-control paths support policy checks and tokenization. Confirm provider enforcement and card access permissions for the selected flow; these mechanisms do not establish compliance certification or eliminate misuse.
- Can the agent ever spend without human approval?
- Supported spend-gated routes check per-transaction, daily and monthly caps and can require approval. Generic x402.pay_url has an optional per-call maximum, not the mandate-bound spend gate.
- What if the agent goes rogue or hallucinates a payment?
- Hard caps and approvals reduce exposure on routes that invoke the spend gate. They do not guarantee protection on every tool or external payment path. Supported spend-gated routes check per-transaction, daily and monthly caps and can require approval. Generic x402.pay_url has an optional per-call maximum, not the mandate-bound spend gate.
- How much does AgentWallet cost?
- Contact the team for current pricing and access terms before integrating.
- Does AgentWallet work with ChatGPT, Claude, Cursor, Devin and LangChain?
- Yes. Each agent's MCP endpoint is a plain URL that drops into Claude Desktop, Cursor, Devin, LangChain, OpenAI Tools and any MCP-compatible client. The permission-scoped tools are vendor-neutral, so the same agent works across Anthropic, OpenAI, Google, xAI and open-source models.
- How is AgentWallet different from Stripe Issuing or Brex?
- Stripe Issuing and Brex issue cards to humans (or, at best, to one virtual proxy per workflow). AgentWallet issues a complete identity per agent — card + bank + USDC + MCP + AP2 + Principal — with policy and audit shaped around autonomous software, not human cardholders. See /vs-link for a full feature comparison.
- How is AgentWallet different from Circle Programmable Wallets?
- Circle Programmable Wallets is a USDC-only smart-wallet SDK — no fiat rails, no virtual card, no MCP, no AP2, no Principal control plane. AgentWallet uses the same on-chain primitives (USDC, EIP-3009) plus configured fiat payout routes, virtual cards, MCP, AP2 and a full identity stack. See /vs/circle for the deep comparison.
- What is x402 and why should I care?
- x402 is the HTTP 402 Payment Required protocol used for machine-to-machine payments — a single round-trip with a signed authorization in a header, no redirect, no UI, no human at a keyboard. It is the protocol AI agents actually use to pay APIs and other agents. AgentWallet implements x402 over EIP-3009 for USDC on Base.
- What is AP2?
- AP2 uses signed intent, cart and payment mandates on supported flows. Mandate signing does not establish a human signature or on-chain anchor for every platform payment.
- What is MCP?
- MCP (Model Context Protocol) is the open standard for connecting LLMs to tools. AgentWallet exposes permission-scoped tools over a per-agent MCP URL that drops into Cursor, Claude Desktop, Devin, LangChain or any MCP-compatible client.
- What security documentation is available?
- This page does not assert compliance certification. Request current scoped security and provider documentation for your review.
- How does AgentWallet do KYC and KYB?
- KYB at the Company tier (the legal entity that owns the AgentWallet account) via Payouts.com. KYC at the Principal tier (the human accountable for an agent's actions) — government ID, liveness check, sanctions screen and a WebAuthn passkey enrolment. Agents are software identity and inherit accountability from their signing Principal.
- Are AI agents allowed to move money under US / EU regulations?
- Legal and regulatory requirements depend on the activity, jurisdiction and provider arrangement. Confirm your intended use with qualified counsel and the relevant providers.
- Can I audit what an AI agent did?
- Ledger and activity records support review of agent actions. Record coverage and identifiers depend on the execution path; there is no universal on-chain trace for every action.
- Where is data stored?
- The application uses Postgres and configured external providers. Confirm deployment regions, subprocessors, backup arrangements and contractual residency requirements with the team.
- What languages does the SDK support?
- TypeScript / JavaScript is first-class with strongly-typed clients generated from our OpenAPI spec. The OpenAPI spec at /docs/openapi.yaml lets you generate idiomatic clients for Python, Go, Rust, Java and any other language that has an OpenAPI generator.
- How do I get a sandbox key?
- Access is invite-only. Ask the team which test environments and provider capabilities are available for your integration; feature parity and setup time are not guaranteed.
- How are webhooks signed and retried?
- Outbound webhooks are signed with X-Payouts-Signature: t=…,v1=hex (Stripe-compatible scheme) keyed by your per-endpoint secret. We retry with exponential backoff (30 s → 1 h cap) for up to 8 attempts, then dead-letter — every attempt auditable in the dashboard.
- What happens if AgentWallet goes down?
- See /status for service information. Request current availability commitments and recovery arrangements from the team; this page does not promise a contractual SLA.
- Is AgentWallet open source?
- AgentWallet integrates MCP, AP2 and x402 interfaces in a hosted platform. Protocol support is not a compliance certification or SLA. Contact the team about deployment and support terms.
- What's on the roadmap?
- v0.6: Members + invitations + RBAC. v0.7: event-sourced ledger with JIT-resource-create approval flow. v0.8: custom MCP tool plugins per account. v0.9: split approval kinds (capability vs allocation). v1.0: on-chain registration on Base mainnet, per-agent MCP server, public agent reputation. Live tracker at /roadmap.
- How do I get started?
- Request access at /sign-up. Integration time and production eligibility depend on account approval and provider setup.