> For the complete documentation index, see [llms.txt](https://docs.doku.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.doku.com/changelog/september-2025/doku-mcp-server.md).

# DOKU MCP Server

Effective Date: September 18th, 2026

DOKU MCP Server enables merchants and developers to integrate DOKU's payment capabilities directly into AI agents and AI-powered applications through the Model Context Protocol (MCP).

As the first Indonesian Payment Service Provider (PSP) to launch an MCP Server, DOKU allows AI applications such as ChatGPT, Claude, and other LLM-powered assistants to perform payment-related actions through a single integration.

With DOKU MCP Server, developers can access 17 payment tools, including creating Checkout links, Virtual Accounts, and QRIS payments. The available tools will continue to grow as new capabilities are introduced.

#### [<mark style="color:$primary;">Explore in DOKU Docs</mark> ](https://docs.doku.com/accept-payments/integration-tools/doku-mcp-server)

***

### 🔍 What’s New?

DOKU now provides an MCP Server that allows AI applications to securely interact with DOKU payment services.

This update ensures:

* Create Checkout Links
* Generate Virtual Accounts
* Generate QRIS Payments
* Access multiple payment tools through a single MCP integration
* Continuously updated payment tools as new capabilities become available

***

### How DOKU MCP Server Works

#### 🔄 **Before This Update**

Developers integrating payment capabilities into AI applications needed to build custom integrations using individual APIs, manually configure authentication, and maintain multiple endpoints:

Steps:

1. Build custom API integration
2. Configure authentication and payment flows
3. Develop payment logic for each use case
4. Maintain integrations as APIs evolve

#### 🆕 **After This Update**

With DOKU MCP Server, AI agents can directly access DOKU payment capabilities through a single MCP integration.

Steps:

1. Connect the AI application to DOKU MCP Server.
2. The AI agent invokes the appropriate payment tool.
3. DOKU processes the request securely.
4. The AI application receives the payment result and continues the workflow.

***

### ✅ Key Details

**First Indonesian PSP with MCP Server**\
DOKU is the first Indonesian Payment Service Provider to introduce an MCP Server for AI-powered payment integrations.

**17 Payment Tools Available**\
Developers can access multiple payment capabilities including Checkout, Virtual Account, and QRIS through a single integration.

**AI-Ready Payment Integration**\
Supports integration with AI agents and Large Language Models (LLMs), including ChatGPT, Claude, and other MCP-compatible applications.

***

### 📌 Important Notes

* To get started with DOKU MCP Server, explore our documentation [here](https://developers.doku.com/accept-payments/doku-mcp-server?utm_source=docs)
* For assistance, contact our Care Team at <care@doku.com> or (021) 1500963.

***

Thank you and best regards,\
**DOKU Product Team**


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.doku.com/changelog/september-2025/doku-mcp-server.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
