# MoltPe

> Use this tool when you need to manage autonomous transactions for AI agents with programmable spending policies and isolated wallets. It solves problems related to secure and controlled USDC stablecoin transactions, offering a range of APIs for balance checks, payments, and invoicing. With support for multiple payment protocols and non-custodial wallets, MoltPe provides a reliable infrastructure for AI agents to perform transactions within predefined spending limits.

Canonical page: https://skillsregistry.net/skills/umg-gpt-moltpe  
JSON: https://api.skillsregistry.net/v1/skills/umg-gpt-moltpe

## Description

AI-native payment infrastructure that gives AI agents isolated wallets with programmable spending policies for autonomous USDC stablecoin transactions.

**11 MCP tools** for Claude Desktop, Cursor, and Windsurf:
- check_balance, send_payment, list_transactions, agent_info
- create_invoice, pay_invoice, check_invoice_status, list_invoices
- call_x402_endpoint, call_mpp_endpoint, plus more

**Tri-rail support:** x402 (HTTP-native micropayments), MPP (session-based streaming), and traditional fiat. Multi-chain USDC on Polygon PoS, Base, and Tempo with sub-second settlement.

**Non-custodial wallets** with Shamir key splitting — your keys, never ours.

**Programmable spending policies** (daily caps, per-transaction caps, recipient allowlists, cooldowns) enforced at the infrastructure level. Your agent literally cannot overspend regardless of prompt injection or buggy retry loops.

**Free tier** — no credit card, no KYC, no geographic gating.

- Site: https://moltpe.com
- Open source reference: https://github.com/umangbuilds/moltpe-agent-payments (Apache 2.0)
- India guide: https://moltpe.com/india
- Developer quickstart: https://moltpe.com/blog/integrate-moltpe-in-5-minutes-developer-quickstart

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/umg-gpt/moltpe)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "umg-gpt-moltpe"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/umg-gpt-moltpe` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/umg-gpt-moltpe/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt
