Stripe Mcp Server

Created By

Lokesh-20252 hours ago

Connect Claude to your Stripe account via natural language. Query customers, revenue, invoices, subscriptions, disputes, and issue refunds — 7 tools, idempotency-safe writes, pinned API version to prevent silent breakage.

Overview Content Tools Comments

Overview

Stripe MCP Server

A Model Context Protocol (MCP) server that connects Claude (or any MCP client) to your Stripe account. Query customers, revenue, invoices, subscriptions, disputes, and issue refunds — all via natural language.

Requirements

Node.js 18+
A Stripe account with a secret API key

Installation

git clone https://github.com/your-username/stripe-mcp-server.git
cd stripe-mcp-server
npm install
cp .env.example .env
# Edit .env and set STRIPE_SECRET_KEY

Running manually

STRIPE_SECRET_KEY=sk_live_... node index.js

Claude Desktop Configuration

Add the following to your claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "stripe": {
      "command": "node",
      "args": ["/absolute/path/to/stripe-mcp-server/index.js"],
      "env": {
        "STRIPE_SECRET_KEY": "sk_live_..."
      }
    }
  }
}

Restart Claude Desktop after editing.

Tools

Tool	Description	Parameters
`list_customers`	List recent Stripe customers	`limit` (1–100, default 10)
`get_revenue`	Total revenue from successful charges in a date range	`from` (YYYY-MM-DD), `to` (YYYY-MM-DD)
`list_invoices`	List invoices by status (`open` = unpaid)	`status` (draft \| open \| paid \| uncollectible \| void)
`list_failed_payments`	List recent failed charges with failure reasons	`limit` (1–100, default 10)
`get_subscription`	Get all subscriptions for a customer	`customer_id` (e.g., `cus_...`)
`create_refund`	Issue a full or partial refund	`charge_id` (e.g., `ch_...`), `amount` (cents, optional)
`list_disputes`	List disputes/chargebacks with evidence deadlines	`limit` (1–100, default 10)

Example prompts

"List my last 20 customers"
"How much revenue did I make in May 2025?"
"Show me all unpaid invoices"
"What failed payments happened recently?"
"Get subscriptions for customer cus_ABC123"
"Refund charge ch_XYZ for $10"
"Are there any open disputes?"

Security

Never commit your .env file or hardcode your secret key.
Use a restricted key with only the permissions your use case needs.
Use sk_test_... keys for development.

License

MIT

Server Config

{
  "mcpServers": {
    "stripe": {
      "command": "node",
      "args": [
        "/path/to/stripe-mcp-server/index.js"
      ],
      "env": {
        "STRIPE_SECRET_KEY": "<YOUR_STRIPE_RESTRICTED_KEY>"
      }
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs

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。

EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

DeepChatYour AI Partner on Desktop

Amap Maps高德地图官方 MCP Server

MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

Howtocook Mcp基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.