SelfPaidPal — Autonomous DeFi Payments
LocalAbout SelfPaidPal — Autonomous DeFi Payments
SelfPaidPal is an MCP server for AI agents that analyzes lending yields and prepares payment transactions on Base Mainnet. It estimates collateral recovery through Aave V3 or Morpho and produces unsigned transaction data, without handling private keys.
Key features
- 01Live Aave V3 and Morpho supply rates
- 02Collateral and recovery-time quotes
- 03Protocol selection by yield
- 04Unsigned EVM transaction data
- 05EIP-5792 batch calls
Use cases
- 01Comparing lending rates on Base
- 02Estimating collateral for payment recovery
- 03Preparing payment transactions for signing
MCP support
The MCP server exposes tools to retrieve rates, calculate quotes, and build unsigned payment transactions and EIP-5792 batches. It connects to the SelfPaid Base Mainnet engine.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y selfpaid-mcpSELFPAID_API_URLSelfPaidPal hosted API endpoint (defaults to https://selfpaid.cryptofolio.it)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
3Saved tool list · updated 1w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| refresh | boolean | No | Force a live on-chain refresh rather than using cached rates (defaults to false). |
Details
From the project README🌾 SelfPaidPal MCP Server
Model Context Protocol (MCP) server for SelfPaidPal — Autonomous, zero-net-cost payments on Base Mainnet (Chain ID 8453) powered by automated yield farming on Aave V3 and Morpho.
This server provides AI agents (Claude, Cursor, Windsurf, OpenClaw) with tools to analyze yield rates, calculate capital recovery timelines, and construct ready-to-sign EVM transactions and atomic EIP-5792 batch calls.
⚡ Features
- Zero External Dependencies: Built with native Node.js HTTP/HTTPS modules. Works out-of-the-box on Node 16, 18, 20, and 22+.
- Non-Custodial: Generates unsigned EVM transaction calldata. Never handles or asks for private keys.
- 100% Capital Recovery: Computes the exact collateral required to reimburse 100% of the payment and fees over time via DeFi yield.
- Multi-Protocol Optimization: Automatically selects the most profitable lending protocol between Aave V3 and Morpho on Base.
🛠️ Exposed MCP Tools
| Tool | Description | Key Parameters |
|---|---|---|
get_rates | Live supply APYs for Aave V3 and Morpho on Base Mainnet. | refresh (boolean, optional) |
get_quote | Calculates required collateral, developer fee, yield deposit, and recovery days. | amount (number, required), protocol (auto/aave/morpho) |
build_payment | Builds 4 EVM transactions & EIP-5792 batch calls ready for signing. | amount, recipient, sender, protocol |
🚀 Installation & Usage
1. Claude Desktop
Add this to your claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"selfpaid": {
"command": "npx",
"args": ["-y", "selfpaid-mcp"]
}
}
}
Or run from a local clone:
{
"mcpServers": {
"selfpaid": {
"command": "node",
"args": ["/path/to/selfpaid-mcp/bin/mcp-server.js"]
}
}
}
2. Cursor / Windsurf
Add a new MCP server in settings:
- Name:
selfpaid - Type:
command - Command:
npx -y selfpaid-mcp
3. Smithery.ai
Install via Smithery CLI:
npx -y @smithery/cli install @al-toninelli/selfpaid-payments --client claude
🌐 Hosted Infrastructure
This client connects to the official SelfPaid Base Mainnet engine:
- API Endpoint:
https://selfpaid.cryptofolio.it - Network: Base Mainnet (Chain ID
8453) - Tokens Supported: Native USDC (
0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913)
⚠️ Risk Disclosure
DeFi deposits carry smart contract, market, and liquidity risks. Transactions on Base Mainnet are irreversible. Principal recovery estimates are dynamic and fluctuate based on market lending yields.
📄 License
MIT License — Copyright (c) 2026 Alessandro Toninelli.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.