@striderlabs/mcp-cashapp
An MCP server that enables AI assistants to automate Cash App payments, balance checks, and transaction management via browser automation.
README
@striderlabs/mcp-cashapp
An MCP (Model Context Protocol) server connector for Cash App payments, powered by Playwright browser automation.
Overview
This package provides an MCP server that exposes Cash App functionality as tools for AI assistants like Claude. It uses Playwright to automate the Cash App web interface.
Installation
npm install -g @striderlabs/mcp-cashapp
Or install from source:
git clone https://github.com/markswendsen-code/mcp-cashapp.git
cd mcp-cashapp
npm install
npm run build
Usage
As an MCP Server
Add to your MCP client configuration (e.g., Claude Desktop's claude_desktop_config.json):
{
"mcpServers": {
"cashapp": {
"command": "striderlabs-mcp-cashapp"
}
}
}
Or run directly:
striderlabs-mcp-cashapp
Prerequisites
- Node.js >= 18
- Playwright Chromium browser (installed automatically with
npm install)
After installing, run:
npx playwright install chromium
Tools
cashapp_login
Log in to Cash App with your credentials. Must be called before any other tool.
Parameters:
email_or_phone(string, required): Email address or phone numberpassword(string, required): Account password
Returns: { success: boolean, message: string }
cashapp_get_balance
Get the current Cash App balance.
Parameters: None
Returns: { balance: string, currency: string }
cashapp_get_transactions
Get recent transaction history.
Parameters:
limit(number, optional): Maximum number of transactions to return (default: 10)
Returns: Array of transaction objects:
[
{
"id": "txn_123",
"type": "sent | received | request",
"amount": 25.00,
"note": "Lunch",
"recipient": "$johndoe",
"date": "Jan 15",
"status": "completed"
}
]
cashapp_get_transaction_details
Get detailed information about a specific transaction.
Parameters:
transaction_id(string, required): Transaction ID
Returns: Single transaction object
cashapp_send_money
Send money to another Cash App user.
Parameters:
recipient(string, required): Recipient's $Cashtag, phone, or emailamount(number, required): Amount in USDnote(string, required): Payment note/memo
Returns: { success: boolean, message: string, transactionId?: string }
cashapp_request_money
Request money from another Cash App user.
Parameters:
recipient(string, required): Recipient's $Cashtag, phone, or emailamount(number, required): Amount in USD to requestnote(string, required): Reason for the request
Returns: { success: boolean, message: string }
cashapp_get_pending_requests
Get all pending payment requests.
Parameters: None
Returns: Array of pending request objects:
[
{
"id": "req_123",
"from": "$janedoe",
"amount": 10.00,
"note": "Coffee",
"date": "Jan 15"
}
]
cashapp_accept_request
Accept a pending payment request.
Parameters:
request_id(string, required): Request ID to accept
Returns: { success: boolean, message: string }
cashapp_decline_request
Decline a pending payment request.
Parameters:
request_id(string, required): Request ID to decline
Returns: { success: boolean, message: string }
cashapp_get_contacts
Get your Cash App contacts/friends list.
Parameters: None
Returns: Array of contact objects:
[
{
"id": "contact_0",
"name": "Jane Doe",
"cashtag": "$janedoe"
}
]
cashapp_get_bitcoin_balance
Get your Bitcoin balance and current USD value.
Parameters: None
Returns: { btcBalance: string, usdValue: string }
cashapp_get_card_info
Get information about your Cash Card.
Parameters: None
Returns:
{
"cardNumber": "•••• •••• •••• 1234",
"status": "Active",
"type": "Cash Card",
"expiryDate": "12/26"
}
cashapp_get_boosts
Get available Cash Card Boosts (discounts).
Parameters: None
Returns: Array of boost objects:
[
{
"name": "10% off DoorDash",
"discount": "10%",
"category": "Food",
"isActive": false
}
]
Example Usage with Claude
You: Please log in to Cash App with my credentials and check my balance.
Claude: I'll use the cashapp_login tool to log in, then check your balance.
[calls cashapp_login]
[calls cashapp_get_balance]
Your Cash App balance is $245.50.
Security Notice
⚠️ Important Security Considerations:
- Never share your Cash App credentials with untrusted parties
- This tool automates real financial transactions — use with caution
- All credentials are only used for the current session and are not stored
- Use only on trusted, secure machines
- Consider using a dedicated account for testing
Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Run in development
npm run dev
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.