home / mcp / stripe mcp server

Stripe MCP Server

This read-only MCP Server allows you to connect to Stripe data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-stripe-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/stripe.prp"
      ]
    }
  }
}

You set up a local, read-only MCP server that exposes live Stripe data via MCP so you can ask natural language questions and receive up-to-date results. This server wraps the CData JDBC Driver for Stripe and presents Stripe data through a simple MCP interface, enabling quick, SQL-free data access for AI assistants running on your machine.

How to use

After you start the MCP server, you connect your MCP client (such as Claude Desktop or another compatible client) to the local process. You don’t need to write SQL queries; you simply ask questions, and the client uses built-in tools to read live Stripe data. Typical uses include locating data tables, inspecting columns, and querying data such as accounts, charges, customers, and invoices. The server operates locally, so the client communicates with the MCP server directly on the same machine.

How to install

Prerequisites: you need a Java Runtime Environment and Maven to build the server locally. Ensure you have a compatible JRE installed and access to the command line.

# 1) Clone the project
git clone https://github.com/cdatasoftware/stripe-mcp-server-by-cdata.git
cd stripe-mcp-server-by-cdata

# 2) Build the server
mvn clean install

Additional setup and configuration details

You will run a local MCP server that reads Stripe data through the CData JDBC Driver. Follow the steps to license the driver, configure a connection, and create a property file that points to your JDBC driver and connection string.

# Step-by-step setup is shown in the configuration guide:
# 1. Download the CData JDBC Driver for Stripe from the vendor site
# 2. License the driver using the provided JAR
# 3. Use the Connection String utility to test and copy the JDBC URL
# 4. Create a stripe.prp file with your connection details

# Example stripe.prp contents (values must be filled with your setup):
Prefix=stripe
ServerName=CDataStripe
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.stripe.jar
DriverClass=cdata.jdbc.stripe.StripeDriver
JdbcUrl=jdbc:stripe:InitiateOAuth=GETANDREFRESH;
Tables=

Running the server

Start the MCP server on the local machine using the Java runtime and the prepared .prp file. The server communicates over stdio, enabling clients running on the same computer to interact with it.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/stripe.prp

Using Claude Desktop or other MCP clients

Configure your MCP client to load the local Stripe MCP. You will add an entry that points the client to the local stdio server. When you start or refresh the client, the Stripe MCP Server appears as an available data source you can query.

Available tools

stripe_get_tables

Retrieves a list of tables available in the Stripe data source. The output is returned in CSV format with a header row of column names.

stripe_get_columns

Retrieves a list of columns for a given table. Use this to discover the available fields in a table. The output is returned in CSV format with a header row of column names.

stripe_run_query

Executes a SQL SELECT query against the Stripe data source and returns the results.