Skip to main content
Glama
akutishevsky

Monobank MCP Server

by akutishevsky

Monobank MCP Server

MCP (Model Context Protocol) server for integrating with Monobank API.

Quick Install

Download the latest .mcpb bundle from the Releases page and open it — Claude Desktop or Claude Code will handle the rest. You'll be prompted to enter your Monobank API token during installation.

Related MCP server: Monobank MCP Server

Prerequisites

Note: Your API token is only used locally and is never tracked or transmitted anywhere except to Monobank's API.

Available Tools

The server provides three tools:

  1. get_currency_rates - Get currency exchange rates. Public endpoint; works without an API token.

  2. get_client_info - Get client information, accounts and jars. Requires a token.

  3. get_statement - Get the statement for an account or jar over a date range. Requires a token. Maximum range is 31 days + 1 hour.

Behaviour worth knowing

  • Amounts are returned in currency units, not cents. A balance of 100,000.00 UAH is reported as 100000, not 10000000. This applies to every monetary field in both get_client_info and get_statement, including commissionRate, which Monobank returns as an absolute amount despite its name.

  • Responses are cached in memory so that Monobank's rate limits are not exceeded: 5 minutes for currency rates, 60 seconds for client info and for each distinct statement query. A repeated call inside that window returns the cached result instead of failing with HTTP 429.

  • Statement dates are ISO 8601 YYYY-MM-DD, interpreted as UTC. The to date is inclusive — a statement from 2024-10-01 to 2024-10-31 covers all of October 31. Omit to to mean "up to now".

  • The statement account parameter defaults to 0, the client's default account. Account and jar identifiers returned by get_client_info are also accepted.

  • MONOBANK_API_TOKEN is only needed for get_client_info and get_statement. The server starts without it and get_currency_rates keeps working; the two authenticated tools return an error explaining that the variable is unset.

MCP Configuration

To use this server with an MCP client, add it to your configuration:

{
  "mcpServers": {
    "monobank": {
      "command": "npx",
      "args": ["monobank-mcp-server"],
      "env": {
        "MONOBANK_API_TOKEN": "your_token_here"
      }
    }
  }
}

Example Prompts

English

  • "Show me the current USD to UAH exchange rate"

  • "Get my account balance and recent transactions"

  • "Show me all transactions from the last week"

  • "What did I spend money on yesterday?"

  • "Show my statement for October 2024"

  • "Get all my credit card transactions from the last 3 days"

Українською

  • "Покажи поточний курс долара"

  • "Скільки грошей на моїх рахунках?"

  • "Покажи виписку за вчора"

  • "На що я витратив гроші цього тижня?"

  • "Покажи всі транзакції за жовтень"

  • "Скільки я витратив на їжу за останній місяць?"

MCPB (One-Click Installation)

This server is available as an MCPB bundle for one-click installation in Claude Desktop and Claude Code.

To build the .mcpb bundle locally:

npm run pack:mcpb

This produces monobank-mcp-server.mcpb which can be installed directly in any MCPB-compatible client. During installation, you'll be prompted to enter your Monobank API token securely.

License

MIT

Available Tools

3 tools
get_client_infoA

Get information about a client and a list of their accounts and jars. The tool can be called not more than 1 time per 60 seconds, otherwise an error will be thrown.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses rate limit (1 per 60s) but does not mention read-only nature or other behavioral traits, leaving gaps without annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, front-loaded purpose, no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose and key constraint; lacks output format details but is adequate for a simple read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist; baseline for 0 parameters is 4. Description correctly avoids adding unnecessary detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states it retrieves client information, accounts, and jars. Distinct from siblings get_currency_rates and get_statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides a rate limit constraint but no guidance on when to use vs alternatives or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_currency_ratesA

Get a basic list of currency rates from Monobank. The information can be refreshed once per 5 minutes, otherwise an error will be thrown.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It discloses the rate limit and error condition, which is important behavioral information. However, it does not detail the return format or other behaviors, so a 4 is given.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, then constraint. No unnecessary words. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity (no params, no output schema), the description covers the source and a key constraint. It might lack details on the return structure, but for a basic list retrieval, it is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has zero parameters, making schema coverage 100%. The description adds no parameter semantics because none are needed. The baseline for 0 parameters is 4, and the description meets that.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and the resource 'a basic list of currency rates from Monobank', distinguishing it from sibling tools like get_client_info and get_statement which serve different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly mentions the refresh rate constraint: 'once per 5 minutes, otherwise an error will be thrown', providing clear guidance on when to use the tool. However, it does not mention alternatives or explicitly state when not to use it, so a 4 is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_statementC

Get Monobank statement for the time from {from} to {to} time in seconds in Unix time format. The maximum time for which it is posssible to obtain a statement is 31 days + 1 hour (2682000 seconds). The statement can be retrieved not more than once per 60 seconds, otherwise an error will be thrown.

ParametersJSON Schema
NameRequiredDescriptionDefault
inputYes

TDQS

C2.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must disclose all behavioral traits. It reveals time and rate limits but contradicts the schema on parameter format (Unix time vs ISO 8601), reducing trustworthiness.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise but contains conflicting information. It front-loads purpose and constraints but sacrifices accuracy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, so description should explain return value; it does not. Contradictions in parameter format make it incomplete. Missing details on statement structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% per context, so description must compensate. Instead, it misrepresents parameter formats (says Unix time, schema says ISO 8601) and only partially describes account (default '0'). No value added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly identifies the tool's purpose: get a Monobank statement for a time range. However, confusion between Unix time (description) and ISO 8601 (schema) slightly diminishes clarity. Sibling tools are distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides constraints on maximum time period (31 days + 1 hour) and rate limit (once per 60 seconds), but no explicit guidance on when to use this tool versus alternatives or when not to use it.

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.

  1. 3 tool updatesv1.2.0
    • First observedget_client_info
    • First observedget_currency_rates
    • First observedget_statement

TDQS

A3.8/5.0

Scored across 3 tools

Disambiguation5/5

Each tool targets a distinct resource: currency rates, client/account info, and transaction statements. No overlap or ambiguity between them.

Naming Consistency5/5

All three tools follow the exact same get_noun pattern, with clear and uniform naming. This is perfectly consistent.

Tool Count5/5

With 3 tools, the server is tightly scoped to the core Monobank personal API endpoints. Each tool earns its place, and the count is ideal for this narrow domain.

Completeness5/5

The server covers all primary read-only Monobank API operations: currency rates, client info, and statements. No obvious gaps exist for the intended functionality, as the API itself offers few other personal endpoints.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    Exposes 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.
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to perform Nigerian banking operations including account management, payments, and identity verification through the Mono Open Banking API.
    59
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to interact with Monzo bank accounts, including checking balances, listing transactions, and managing pots through natural language via the MCP protocol.
    8 npm
    MIT