Does MoltPe work with Claude Desktop?
Yes. MoltPe ships an MCP (Model Context Protocol) server that plugs directly into Claude Desktop's MCP configuration. After adding MoltPe's server to claude_desktop_config.json and restarting Claude Desktop, the MoltPe tools (create agent wallet, set spending policy, send payment, check balance, list transactions, generate invoice, verify payment) appear in Claude's tool picker. Claude can then autonomously manage agent wallets and send USDC payments within the spending policies you configure. MoltPe is AI-native payment infrastructure that gives AI agents isolated wallets with programmable spending policies for autonomous USDC stablecoin transactions.
The short version
- Add to config: Drop the MoltPe MCP server entry into
claude_desktop_config.jsonwith your API key, then restart Claude Desktop. Setup takes under two minutes. - Tools available in Claude: create agent wallet, set spending policy, send payment, check balance, list transactions, generate invoice, verify payment — all exposed as native Claude tools.
- Payments flow: You describe the intent in plain English; Claude calls the MoltPe tools; MoltPe enforces your spending policy; USDC settles on Polygon, Base, or Tempo.
In more detail
Model Context Protocol (MCP) is the open standard Anthropic introduced for connecting Claude to external tools and data sources. MoltPe's MCP server speaks MCP natively, which means any MCP-compatible client — Claude Desktop, Claude Code, and a growing list of third-party agent frameworks — can call MoltPe without custom integration work.
The setup is a three-line change to the Claude Desktop config file. You tell Claude Desktop where the MoltPe MCP server lives, pass your MoltPe API key, and restart the app. Claude picks up the new tools automatically. From then on, prompts like "pay 5 USDC to the invoice on this page" or "show me last week's agent spend" get routed through the MoltPe tools, and Claude sees the tool responses inline. The full tool list covers wallet lifecycle (create, list, pause), policy management (daily cap, per-tx cap, recipient allowlist), the send flow (payment, balance, transaction history), and the merchant side (invoice creation, payment verification).
Every action Claude initiates is gated by your spending policy. Claude cannot raise caps, add recipients, or disable the policy — those are owner-only actions taken from the MoltPe dashboard. That separation means you can give Claude agency to act autonomously while keeping hard limits on financial exposure. Exactly the same MCP server works with Claude Code, Cursor, and any MCP-aware agent runtime, so you configure once and use everywhere.
Related questions
- Blog: MCP server for AI agent payments
- What is MCP (Model Context Protocol)?
- How do AI agents make payments?
- Blog: Integrate MoltPe in 5 minutes — developer quickstart
About MoltPe
MoltPe is AI-native payment infrastructure that gives AI agents isolated wallets with programmable spending policies for autonomous USDC stablecoin transactions. Live on Polygon PoS, Base, and Tempo.