Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready Paddle MCP server with 54 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across Paddle — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Paddle MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Paddle tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Paddle call.
Tools Discovery →A Paddle MCP server lets AI agents read and write Paddle data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Paddle MCP server ships with 54 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
Every action from Paddle's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Create a new address for a customer
Get an address for a customer by ID
Update an address for a customer
Create a new business for a customer
Retrieve a specific business for a customer
Update a business for a customer
Create a new customer
Retrieve a paginated list of customers
Get a customer by ID
Update a customer
Create a new discount group
Retrieve a paginated list of discount groups
Retrieve a specific discount group by ID
Update a discount group
Create a new discount
Retrieve a paginated list of discounts
Retrieve a specific discount by ID
Update a discount
Retrieve a paginated list of notifications from the last 90 days
Retrieve a specific notification
Retrieve a paginated list of payment methods for a customer
Retrieve a specific payment method for a customer
Delete a payment method for a customer
Create a new price
Retrieve a paginated list of prices
Get a price by ID
Update a price
Create a new product
Retrieve a paginated list of products
Get a product by ID
Update a product
Retrieve a paginated list of subscriptions
Retrieve a specific subscription
Update a subscription using its ID
Create a new transaction
Retrieve a paginated list of transactions
Retrieve a specific transaction
Update a transaction
Create a one-time charge for a subscription
Retrieve a paginated list of addresses for a customer
Retrieve a paginated list of businesses for a customer
List credit balances for a customer
Retrieve a paginated list of events from the event stream
Retrieve a list of all event types
Generate and retrieve invoice PDF for a transaction
Generate authentication token for a customer
Resend a delivered or failed notification
Preview calculations for one or more prices
Preview a one-time charge for a subscription without billing
Pause a subscription
Resume a paused subscription
Cancel a subscription
Activate a trialing subscription
Update customer and address information for a transaction
One endpoint. Any framework. Your agent is talking to Paddle in under 10 lines of code.
MCP Clients
Agent Frameworks
{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}162+ actions
133+ actions
125+ actions
125+ actions
120+ actions
73+ actions
69+ actions
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.