A
licenseNot graded
qualityA
maintenanceDeterministic, auditable payment policy enforcement for AI agents. It provides pre-action authorization with scopes, budgets, allowlists, and signed mandates via an MCP server.
MIT
dingdawg-agent-wallet
by dingdawg
Integrates with Coinbase AgentKit to add policy enforcement (allow/deny/step-up/allowlist) and an immutable audit trail for agent wallets holding and spending USDC.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@dingdawg-agent-walletProvision a wallet with daily cap 200 USDC and per-call cap 50 USDC"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
dingdawg-agent-wallet — live demo
Shows governed agent wallet enforcement in action: allow, deny, step-up, allowlist — all in 5 seconds. No API keys. No blockchain required.
What it demonstrates
▶ provision_wallet
wallet_id: demo-wallet-abc123
daily_cap: $200 USDC
per_call_cap: $100 USDC
▶ governed_spend — $25 USDC (allowed)
✓ AUTHORIZED
receipt_id: 6aba84a6-...
daily_remaining: $175 USDC
next_step: wallet.sendToken({ assetId: "usdc", amount: "25", destination: "0xVendorABC123" })
▶ governed_spend — $150 USDC (exceeds per-call cap)
✗ DENIED
reason: Amount 150 USDC exceeds per-call cap 100 USDC
receipt_id: cd7a7aa8-... (denial is logged too)
▶ governed_spend — $75 USDC (step-up required)
⚠ STEP-UP REQUIRED
reason: Amount 75 USDC > step-up threshold 50 USDC — MFA required
fix: Pass approval_token from your authorization flow
▶ governed_spend — unknown recipient (not in allowlist)
✗ DENIED
reason: Recipient 0xUnknownAddress not in allowlist
▶ wallet_audit
chain_verified: true ✓
total_receipts: 5
[17:02:18] DENY $10 USDC governed_spend
[17:02:18] DENY $75 USDC governed_spend
[17:02:18] DENY $150 USDC governed_spend
[17:02:18] ALLOW $25 USDC governed_spend
[17:02:18] ALLOW provision_walletEvery action — allow AND deny — produces an immutable receipt. chain_verified: true means the full chain is tamper-evident — any modification is detectable.
Related MCP server: spendveto
Run it
git clone https://github.com/DingDawg/agent-wallet-demo
cd agent-wallet-demo
npm install
node demo.mjsThe package
dingdawg-agent-wallet — 5 MCP tools that wrap any agent wallet with policy enforcement and an immutable audit trail.
npm install dingdawg-agent-walletTool | What it does |
| Create wallet with spend policy (daily cap, per-call cap, allowlist) |
| Policy check → authorize → immutable receipt |
| Accept payment with tamper-evident receipt |
| Update limits and allowlists at runtime |
| Full receipt chain — |
Coinbase AgentKit gives your agent a wallet. DingDawg gives it a conscience.
Why this matters
AI agents can now hold USDC and spend autonomously. The infrastructure exists. What doesn't: who enforces what the agent is allowed to spend, on what, for whom — and proves it happened correctly.
governed_spendauthorizes then returns the exactagentkit_callSDK method to execute on-chainEvery denial is logged — you can prove what your agent didn't do
chain_verified: truemeans the audit trail is tamper-evident — any modification is detectable
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
Crypto transaction firewall and risk tools for MCP agents.
Pre-spend firewall for AI agents. Approves, blocks, flags transactions against policy rules.
- gatewayOAuthai.sealgate
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
MCP enforcement layer that intercepts AI agent actions and blocks rule violations before execution.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceGoverns AI agents' spending by enforcing budgets, approvals, and kill switches before any payment, providing an MCP interface for tool calls with policy checks.1Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnforces spend policies on Razorpay MCP tool calls by applying per-agent spend caps, category allowlists, and approval thresholds, with a tamper-evident audit ledger.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to screen proposed actions, enforce deterministic policies and limits, and produce tamper-proof signed audit receipts before any external side effect is executed.2 npmMIT