PayPls MCP Server
Enables AI agents to manage Bitcoin and USDC payments by checking balances, sending funds, and generating receive addresses through the PayPls platform. It facilitates secure financial automation with features like transaction tracking and configurable human approval limits.
README
PayPls MCP Server
MCP (Model Context Protocol) server that enables AI agents to manage Bitcoin and USDC payments through PayPls.
What is this?
⚠️ Important: This MCP server does NOT enforce spending limits or approval requirements. All limits are configured and enforced by the PayPls backend. Configure your limits in the PayPls Dashboard before giving agents access to real funds.
This server allows AI assistants like Claude to:
- 💰 Check wallet balances (BTC and USDC)
- 📤 Send payments with human approval
- 📥 Generate receive addresses
- 📋 List wallet buckets
- 🔍 Track transaction status
All transactions can be configured to require human approval above certain thresholds, giving you control while enabling AI autonomy for small payments.
Installation
npm install -g @paypls/mcp-server
Or run directly with npx:
npx @paypls/mcp-server
Configuration
1. Get your API token
Sign up at paypls.io and generate an API token in Settings → API Keys.
2. Set environment variables
Create a .env file or set these environment variables:
# Required: Your PayPls API token
PAYPLS_TOKEN=your_token_here
# Optional: API URL (defaults to https://api.paypls.io)
PAYPLS_API_URL=https://api.paypls.io
3. Configure Claude Desktop
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"paypls": {
"command": "npx",
"args": ["@paypls/mcp-server"],
"env": {
"PAYPLS_TOKEN": "your_token_here"
}
}
}
}
Or if installed globally:
{
"mcpServers": {
"paypls": {
"command": "paypls-mcp",
"env": {
"PAYPLS_TOKEN": "your_token_here"
}
}
}
}
Available Tools
| Tool | Description |
|---|---|
wallet_balance |
Check BTC or USDC balance of a bucket |
wallet_list_buckets |
List all wallet buckets with balances |
wallet_send_btc |
Send Bitcoin to an address |
wallet_send_usdc |
Send USDC to an address |
wallet_receive |
Get an address to receive funds |
wallet_tx_status |
Check transaction status |
Example Usage
Once configured, you can ask Claude things like:
- "What's my Bitcoin balance?"
- "Send 10,000 sats to bc1q... for the API subscription"
- "Send $25 USDC to 0x... for the design work"
- "Generate a receive address for Bitcoin"
- "Check the status of transaction abc-123"
Security
- Human approval: Configure auto-approve limits in the PayPls dashboard. Transactions above the limit require explicit approval.
- Justifications: Every send requires a justification that's logged and shown during approval.
- Bucket isolation: Use separate buckets to limit agent access to specific funds.
- Token permissions: API tokens can be scoped to specific actions and buckets.
Handling Approval Flows
When a transaction exceeds auto-approve limits, the API returns:
{
"status": "pending_approval",
"transaction_id": "...",
"message": "Awaiting human approval"
}
Your agent should:
- Inform the user that approval is needed
- Optionally poll
/agent/tx/:idto check status - NOT retry the same transaction (use idempotency keys)
Development
# Clone the repository
git clone https://github.com/paypls/mcp-server.git
cd mcp-server
# Install dependencies
npm install
# Run in development mode
PAYPLS_TOKEN=your_token npm run dev
# Build
npm run build
# Type check
npm run typecheck
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
PAYPLS_TOKEN |
Yes | - | Your PayPls API token |
PAYPLS_API_URL |
No | https://api.paypls.io |
API endpoint URL |
Support
- 📖 Documentation
- 💬 Discord
- 🐛 Issues
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。