Проект для управления израильскими банковскими счетами и транзакциями с использованием протокола Model Context Protocol (MCP).
Список доступных израильских банков и компаний, выпускающих кредитные карты, с указанием необходимых учетных данных
Получение транзакций из любого поддерживаемого банка
Поддержка всех основных израильских банков и компаний, выпускающих кредитные карты
Безопасная обработка учетных данных
Гибкие диапазоны дат транзакций
Поддержка двухфакторной аутентификации
Related MCP server: MoneyWiz MCP Server
Установите зависимости:
npm installСоберите проект:
npm run buildПодключитесь к MCP-клиентам
Сервер можно подключить к любому MCP-совместимому клиенту. Вот как его настроить:
Учетные данные считываются из переменных окружения (никогда из аргументов инструментов — это позволяет избежать их утечки в историю диалога с LLM). Для каждого банка требуются переменные окружения <BANK_ID>_<FIELD>. Например, для банка Leumi нужны LEUMI_USERNAME и LEUMI_PASSWORD; для Hapoalim — HAPOALIM_USERCODE и HAPOALIM_PASSWORD. Используйте ресурс banks://list, чтобы увидеть имена необходимых переменных окружения для каждого банка.
Для клиентов, поддерживающих файлы конфигурации (например, Claude), добавьте следующее в свою конфигурацию:
{
"mcpServers": {
"israeli-bank-mcp": {
"command": "node",
"args": [
"/path/to/israeli-bank-mcp/build/server.js"
],
"env": {
"LEUMI_USERNAME": "your-username",
"LEUMI_PASSWORD": "your-password"
}
}
}
}Банки (banks://list)
Список доступных банков и необходимых для них учетных данных
Получение транзакций (fetch-transactions)
Получение транзакций из банка
2FA (two-factor-auth)
Двухфакторная аутентификация для банков, которые ее требуют
Сервер поддерживает все основные израильские банки и компании, выпускающие кредитные карты, через библиотеку israeli-bank-scrapers:
Bank Hapoalim
Leumi Bank
Discount Bank
Mercantile Bank
Mizrahi Bank
Otsar Hahayal Bank
Visa Cal
Max (ранее Leumi Card)
Isracard
Amex
Union Bank
Beinleumi
Massad
Yahav
Beyhad Bishvilha
OneZero (экспериментально)
Behatsdaa
Пожалуйста, не пытайтесь делать это дома (честно говоря, я не знаю, вероятно, это не лучшая идея, но это очень круто)
MIT
| Name | Required | Description | Default |
|---|---|---|---|
| bankId | Yes | ||
| combineInstallments | No | ||
| credentials | Yes | ||
| showBrowser | No | ||
| startDate | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | ||
| bankId | Yes | ||
| otpCode | No | ||
| phoneNumber | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0fetch-transactionstwo-factor-authScored across 2 tools
The two tools have clearly distinct purposes: 'fetch-transactions' retrieves transaction data, while 'two-factor-auth' handles authentication. There is no overlap or ambiguity between these functions, making it easy for an agent to select the correct tool.
Both tools use a consistent verb-noun pattern with hyphens (e.g., 'fetch-transactions', 'two-factor-auth'), which is predictable and readable. The minor deviation is that 'two-factor-auth' uses a compound noun without a clear verb, but overall the naming is coherent.
With only two tools, the server feels thin for a banking domain, which typically requires operations like account management, transfers, balances, or payments. This limited set may not cover essential banking workflows, indicating an under-scoped tool surface.
The tool set is severely incomplete for a banking server. It lacks basic operations such as checking account balances, initiating transfers, managing accounts, or handling payments. The two tools provided do not form a functional banking interface, leading to significant gaps that will cause agent failures.
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
