bangladesh-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Tools for Bangladesh: individual income tax (NBR bands, categories, investment rebate, minimum tax), taka amounts in words in English or Bangla (lakh/crore), mobile number validation with operator detection, loan EMI, DPS/savings growth, Bangla digit conversion and a safe maths expression calculator. All money values are in BDT. Tax results are estimates; tell users to confirm with the latest NBR rules.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| income_taxA | Calculate Bangladesh individual income tax. Args: income: Annual income in BDT by source, e.g. {"salary": 800000, "house_rent": 50000}. investment: Eligible rebate investments in BDT, e.g. {"sanchaypatra": 60000, "dps": 40000}. category: One of general, female, senior, disabled, freedom-fighter, third-gender. |
| amount_in_wordsA | Write a taka amount in words for invoices and cheques, using lakh/crore. Args: amount: Amount in BDT; up to two decimals are read as paisa. language: "en" for English or "bn" for Bangla. include_only: Add "Only" / "মাত্র" at the end. |
| check_mobile_numbersA | Validate Bangladeshi mobile numbers, normalise them to +880 format and detect the operator. Args: numbers: Numbers in any common format, e.g. "01712-345678", "+880 1912 345678", Bangla digits. |
| calculate_expressionA | Evaluate a maths expression safely, e.g. "2*sin(30) + sqrt(16) + 5!". Args: expression: Supports + - * / // % ^ **, parentheses, !, pi, e, tau and sqrt, cbrt, root, exp, log, ln, sin, cos, tan, asin, acos, atan, factorial, abs, power, percent, mod. angle_unit: "deg" (default) or "rad" for trigonometric functions. |
| loan_emiA | Equal monthly instalment (EMI) for a loan, with total interest. Args: principal: Loan amount in BDT. annual_rate_percent: Yearly interest rate, e.g. 12 for 12%. months: Loan term in months. |
| savings_growthB | Future value of a lump sum plus monthly deposits (DPS/FDR), compounded monthly. Args: principal: Starting amount in BDT (0 for a plain DPS). monthly_deposit: Amount deposited every month in BDT. annual_rate_percent: Yearly interest rate, e.g. 9 for 9%. months: Number of months. |
| convert_digitsA | Convert digits between English and Bangla. Args: text: Any text containing digits. to: "bn" for Bangla digits (০-৯) or "en" for English digits (0-9). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a clearly distinct operation: tax computation, number-to-words, mobile validation, generic expression evaluation, loan EMI, savings growth, and digit script conversion. The three financial tools (income_tax, loan_emi, savings_growth) are adjacent but their descriptions make the boundaries unambiguous. No two tools appear to do the same thing.
The set mixes verb-first names (check_mobile_numbers, calculate_expression, convert_digits) with noun-phrase names (income_tax, amount_in_words, loan_emi, savings_growth). All are snake_case and readable, but there is no single predictable verb_noun pattern, so an agent cannot infer the naming scheme of a new tool.
Seven tools is well within the sweet spot and each one covers a discrete, useful capability with no filler. Nothing feels redundant or missing at the count level.
The surface covers the core Bangladeshi finance/text utilities: tax, EMI, savings, amount wording, mobile validation, digit conversion, plus a general math evaluator. Minor gaps remain (e.g. VAT/corporate tax, parsing words back to amounts, or a currency formatter), but agents can work around them with calculate_expression.