Monobank MCP Server
Monobank MCP Server (Node.js/TypeScript)
Node.js/TypeScript реализация Monobank MCP Server, изначально написанного на Python.
Monobank MCP Server предоставляет доступ к вашему личному счету Monobank (и публичным курсам валют) в качестве инструментов протокола Model Context Protocol (MCP).
Об этой версии
Это Node.js/TypeScript порт оригинальной реализации на Python от @nklymok.
Оригинальная версия на Python: https://github.com/nklymok/Monobank-MCP
Эта версия на TypeScript: Сохраняет те же основные инструменты для работы с личным счетом, используя преимущества экосистемы Node.js/TypeScript, а также добавляет инструмент для получения публичных курсов валют, не требующий токена.
Related MCP server: Monobank MCP Server
Возможности
MCP-сервер на TypeScript/Node.js с использованием официального
@modelcontextprotocol/sdkИнструменты MCP:
get_client_info– информация о клиенте, счетах и банках (требуетсяMONOBANK_API_TOKEN).get_statement– выписка по счету за временной интервал (требуется токен). Проверяет период перед вызовом API; ответы содержат суммы в основных единицах и время транзакций в формате ISO 8601 UTC.get_currency_rates– публичные курсы обмена валют от Monobank (GET /bank/currency). API-токен не требуется.
Использование (опубликованный пакет)
Самый простой способ использовать этот MCP-сервер — через опубликованный npm-пакет:
Зарегистрируйте сервер в вашей конфигурации MCP
{ "mcpServers": { "monobank-mcp": { "command": "npx", "args": ["-y", "@alerix/monobank-mcp"], "env": { "MONOBANK_API_TOKEN": "your_token_here" } } } }Установите
MONOBANK_API_TOKENтолько если вы используетеget_client_infoилиget_statement.get_currency_ratesработает без него.Запустите ваш MCP-клиент – инструменты будут доступны в соответствии с вашей конфигурацией.
Разработка
Если вы хотите внести свой вклад или изменить сервер:
Клонируйте репозиторий и установите зависимости
git clone https://github.com/aler1x/monobank-mcp.git cd monobank-mcp npm installЗапустите сервер после установки (
prepareвыполняетnpm run build). Для личных инструментов установитеMONOBANK_API_TOKEN.Windows (PowerShell):
$env:MONOBANK_API_TOKEN="your_token_here" node dist/index.jsWindows (Командная строка):
set MONOBANK_API_TOKEN=your_token_here node dist\index.jsmacOS/Linux:
export MONOBANK_API_TOKEN=your_token_here node dist/index.jsИли одной строкой:
MONOBANK_API_TOKEN=your_token_here node dist/index.jsРазработка с горячей перезагрузкой (использует
tsx --watch):MONOBANK_API_TOKEN=your_token_here npm run devСборка (TypeScript →
dist/):npm run build
Справочник инструментов
Инструмент | Описание | Токен | Лимиты запросов (Monobank) |
| Получает профиль клиента, список счетов и банок. | Да | 1 запрос / 60 с |
| Получает транзакции для счета за период. Параметры: | Да | 1 запрос / 60 с |
| Публичные курсы валют (числовые коды валют ISO 4217). Те же данные, что и в Monobank | Нет | Согласно публичному API Monobank |
API-токен
Для личных инструментов требуется персональный API-токен Monobank. См. официальную документацию: https://api.monobank.ua/index.html
Переменные окружения
Имя | Обязательно | Описание |
| Только для | Ваш персональный API-токен Monobank с сайта https://api.monobank.ua/index.html. Не используется для |
Лицензия
MIT
Available Tools
2 toolsget_client_infoA
Get client information from Monobank API. This tool retrieves information about the client, their accounts, and jars. It requires a Monobank API token with the necessary permissions.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the authentication requirement (API token with permissions) which is valuable context, but doesn't describe what information is returned, whether there are rate limits, error conditions, or other behavioral traits. It adequately covers the basic operation but lacks detail about the tool's behavior.
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?
The description is appropriately concise with two sentences that each add value. The first sentence states the purpose, and the second adds important context about authentication requirements. There's no wasted text, though it could be slightly more structured.
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?
Given that this is a read operation with no parameters and no output schema, the description provides adequate but minimal information. It covers the purpose and authentication requirements, but doesn't describe what specific information is returned or the format of the response. For a tool that retrieves client information, more detail about the return data would be helpful.
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?
The tool has 0 parameters with 100% schema description coverage, so the schema already fully documents the parameter situation. The description doesn't need to add parameter information, and it appropriately doesn't discuss parameters. The baseline for 0 parameters with full schema coverage is 4.
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?
The description clearly states the tool's purpose: 'Get client information from Monobank API' with specific resources mentioned (client, accounts, jars). It distinguishes from the sibling tool 'get_statement' by focusing on client metadata rather than transaction data. However, it doesn't explicitly contrast with the sibling, so it's not a perfect 5.
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?
The description provides some usage context by mentioning the required API token and permissions, but doesn't explicitly state when to use this tool versus alternatives. It implies usage for retrieving client metadata but doesn't provide guidance about when not to use it or what the sibling tool 'get_statement' is for.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_statementA
Get account statement for a given period. Rate limit: 1 request per 60 seconds. Max period: 31 days + 1 hour. Rules: 1. Fetch from default account (account_id = '0') unless another account is specified. 2. Amounts are converted from the smallest currency unit (e.g., kopiyka, cent) to the main unit and returned as decimals. 3. Transaction timestamps ('time') are converted from Unix timestamps to ISO 8601 datetime strings (UTC). 4. Fields 'id', 'invoiceId', 'counterEdrpou', and 'counterIban' are omitted from the returned results.
| Name | Required | Description | Default |
|---|---|---|---|
| account_id | Yes | Account identifier from the list of accounts, or '0' for default | |
| from_timestamp | Yes | Start of the statement period (Unix timestamp) | |
| to_timestamp | Yes | End of the statement period (Unix timestamp) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes rate limits ('1 request per 60 seconds'), constraints ('Max period: 31 days + 1 hour'), data transformation rules (currency conversion, timestamp formatting), and output filtering (omitted fields), providing comprehensive behavioral context.
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?
The description is efficiently structured with a clear purpose statement followed by rate limits, constraints, and specific rules in a numbered list format. Every sentence adds value without redundancy, making it easy to parse and understand.
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?
For a tool with no annotations and no output schema, the description does an excellent job covering behavioral aspects, constraints, and data transformations. However, it doesn't explicitly describe the return format or structure of the statement data, which would be helpful given the lack of output schema.
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?
The schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds some context about default account behavior ('account_id = '0' unless another is specified') and timestamp usage, but doesn't provide significant additional parameter meaning beyond what the schema offers.
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?
The description clearly states the specific action ('Get account statement') and resource ('for a given period'), distinguishing it from the sibling tool 'get_client_info' which presumably retrieves different information. It provides concrete details about what the tool does beyond just the name.
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?
The description implies usage by specifying a period requirement and default account behavior, but it doesn't explicitly state when to use this tool versus alternatives or provide any exclusion criteria. It offers some context but lacks explicit guidance on tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
- First observed
get_client_info - First observed
get_statement
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: get_client_info retrieves client metadata, accounts, and jars, while get_statement fetches transaction data for a specific period. There is no overlap or ambiguity between these functions.
Both tools follow a consistent verb_noun naming pattern (get_client_info, get_statement) with identical verb style and snake_case formatting, making them predictable and easy to understand.
With only two tools, the server feels severely under-scoped for a banking API. Key operations like creating transactions, managing accounts, or updating client details are missing, limiting its utility for comprehensive financial tasks.
The toolset is highly incomplete for a banking domain. It only supports read operations (get_client_info, get_statement) with no ability to perform writes (e.g., transfers, payments), updates, or deletions, leaving significant gaps in typical banking workflows.
Maintenance
Related MCP Connectors
Wise (https://wise.com) MCP, multi-currency account access via Personal Token + SCA key. Reads profi
An MCP server that provides read access to your cloud storage providers, bank accounts and more.
Personal finance for AI agents — onboard, import statements, categorize & budget over MCP.
Brazilian Open Finance MCP — 30+ banks (Itaú, Nubank, etc.) to Claude/Cursor. Read-only.
Related MCP Servers
- AlicenseAqualityAmaintenanceEnables integration with Monobank API to check currency exchange rates, view account balances, and retrieve transaction statements through natural language queries.344 npm11MIT
- FlicenseNot gradedqualityDmaintenanceExposes Monobank personal account data through MCP tools, allowing users to fetch client info, accounts, and jars. It also enables retrieving account statements for specific time periods.-
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI assistants to retrieve and format Monobank account statements and transactions by date range.6 npm4MIT
- AlicenseCqualityDmaintenanceEnables interaction with Monarch Money data via MCP tools for accounts, budgets, and transactions.628 npm4MIT