Can I use Paddle as a CLI?

Yes. KosmoKrator exposes a Paddle CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Paddle through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Paddle tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Paddle credentials stored?

Paddle credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Paddle MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

other

Paddle MCP Integration for Vercel AI SDK

Connect Paddle to Vercel AI SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.

7 functions 6 read 1 write Bearer token auth

Submit Paddle feedback View package source

Connect Paddle to Vercel AI SDK

Use KosmoKrator as a local integration gateway for Vercel AI SDK agents and scripts.

Create an MCP client that starts or connects to the KosmoKrator gateway for the selected integration. The gateway is local, scoped to this integration, and starts with --write=deny so Vercel AI SDK can inspect read-capable tools without receiving write access by default.

Paddle MCP Config for Vercel AI SDK

Prefer CLI JSON calls when a workflow only needs one deterministic integration operation.

{
  "mcpServers": {
    "kosmokrator-paddle": {
      "type": "stdio",
      "command": "kosmo",
      "args": [
        "mcp:serve",
        "--integration=paddle",
        "--write=deny"
      ]
    }
  }
}

Run the Gateway Manually

kosmokrator mcp:serve --integration=paddle --write=deny

Why Use KosmoKrator Here

Scoped tools

Expose only Paddle instead of a broad multi-service tool list.

Local credentials

Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.

Write policy

Start read-only, then opt into ask or allow for trusted workspaces.

Paddle Tools Visible to Vercel AI SDK

Vercel AI SDK sees stable MCP tool names generated from the Paddle integration catalog.

MCP tool	Source function	Type	Description
`integration__paddle__paddle_list_transactions`	`paddle.paddle_list_transactions`	Read	List Paddle transactions. Supports filtering by status and customer ID, with cursor-based pagination.
`integration__paddle__paddle_get_transaction`	`paddle.paddle_get_transaction`	Read	Get detailed information about a specific Paddle transaction by its ID.
`integration__paddle__paddle_list_customers`	`paddle.paddle_list_customers`	Read	List Paddle customers. Supports filtering by email and name, with cursor-based pagination.
`integration__paddle__paddle_get_customer`	`paddle.paddle_get_customer`	Read	Get detailed information about a specific Paddle customer by their ID.
`integration__paddle__paddle_create_customer`	`paddle.paddle_create_customer`	Write	Create a new customer in Paddle. An email address is required.
`integration__paddle__paddle_list_products`	`paddle.paddle_list_products`	Read	List Paddle products. Supports filtering by status with cursor-based pagination.
`integration__paddle__paddle_get_current_user`	`paddle.paddle_get_current_user`	Read	Verify Paddle API connectivity by performing a health check request. Returns connection status and API response.

Related Paddle Pages

Paddle CLIUse direct JSON commands instead of MCP discovery. Paddle MCPFull gateway reference and MCP tool names. KosmoKrator for Vercel AI SDKClient-level gateway setup.