Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

Bunq Partner

БесплатноНе проверен

An MCP server that connects AI assistants to the bunq Partner API, enabling natural language management of partner onboarding, including provisioning users, KYC

GitHubEmbed

Описание

An MCP server that connects AI assistants to the bunq Partner API, enabling natural language management of partner onboarding, including provisioning users, KYC, accounts, payments, cards, and compliance.

README

An MCP (Model Context Protocol) server that connects AI assistants like Claude to the bunq Partner API. Once set up, you can drive the entire partner onboarding flow — provisioning users, KYC, accounts, payments, cards, and compliance — through natural language conversation.

What you can do

After connecting, you can ask Claude things like:

  • "Provision a new user with email [email protected] and phone +31612345678"
  • "Check the status of provision 4521"
  • "Create a EUR bank account for user 8823"
  • "Make a payment of €50 from account 12 to IBAN NL91ABNA0417164300"
  • "Show me all open compliance inquiries for user 9002"
  • "Register a webhook for mutations on user 8823 pointing to https://myapp.com/webhooks"

Claude handles the full auth lifecycle, request signing, token management, and status polling automatically.

Prerequisites

Setup

1. Clone and build

git clone https://github.com/bunq/partner-mcp.git
cd partner-mcp
npm install
npm run build

2. Add to Claude Desktop

Edit your Claude Desktop config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "bunq-partner": {
      "command": "node",
      "args": ["/absolute/path/to/partner-mcp/dist/index.js"],
      "env": {
        "BUNQ_API_KEY": "your_partner_api_key_here",
        "BUNQ_ENV": "sandbox"
      }
    }
  }
}

Replace /absolute/path/to/partner-mcp with the actual path where you cloned the repo.

3. Restart Claude Desktop

Quit and reopen Claude Desktop. You should see the bunq tools available.

4. Verify the connection

Ask Claude: "Check my bunq session info" — it should respond with your authenticated user ID and environment.

Environments

BUNQ_ENV Base URL
sandbox (default) https://partner-api.sandbox.bunq.com
production https://api.partner.bunq.com

Always test in sandbox first. Sandbox API keys contain a sandbox_ prefix.

Updating

When a new version is released:

cd partner-mcp
git pull
npm install
npm run build

Then restart Claude Desktop.

Available tools (41)

See docs/ for the full documentation, or browse by chapter:

Project structure

partner-mcp/
├── src/
│   ├── index.ts          # MCP server entry point (stdio transport)
│   ├── bunq-client.ts    # HTTP client + auth lifecycle
│   ├── tools.ts          # Tool definitions (MCP schemas)
│   └── handler.ts        # Tool → API call mapping
├── docs/                 # Documentation (synced to GitBook)
├── scripts/
│   └── UPDATE.md         # Script to update MCP + docs from GitLab MRs
├── package.json
└── tsconfig.json

Support

from github.com/bunq/partner-mcp

Установка Bunq Partner

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/bunq/partner-mcp

FAQ

Bunq Partner MCP бесплатный?

Да, Bunq Partner MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для Bunq Partner?

Нет, Bunq Partner работает без API-ключей и переменных окружения.

Bunq Partner — hosted или self-hosted?

Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.

Как установить Bunq Partner в Claude Desktop, Claude Code или Cursor?

Открой Bunq Partner на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Compare Bunq Partner with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории ai