finpilot
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FINPILOT_STATEMENT | No | Path to the bank statement CSV file to load by default. Optional: if not set, the assistant can call the load_statement tool with a file path instead. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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 |
|---|---|
| load_statementC | Загрузить выписку (CSV Т-Банка или CSV с колонками date, amount, description). Возвращает период и итоги. |
| spending_by_categoryA | Расходы по категориям за месяц (YYYY-MM, по умолчанию последний) и изменение к прошлому месяцу. |
| top_merchantsC | Магазины и сервисы, на которые ушло больше всего денег за месяц. |
| find_subscriptionsA | Регулярные списания (подписки): сумма, периодичность, дата следующего списания, стоимость в год. |
| find_unusual_transactionsC | Операции крупнее обычного для своей категории и возможные двойные списания. |
| forecast_monthB | Прогноз расходов до конца последнего месяца выписки при текущем темпе трат. |
| search_transactionsC | Найти операции по тексту описания или по названию категории. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| monthly_review | Шаблон запроса: разбор расходов за месяц с выводами. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a distinct analysis task: ingestion, category aggregation, merchant aggregation, subscription detection, forecasting, anomaly detection, and text search. Boundaries are clear, and no two tools overlap significantly.
All names use snake_case and are readable, but verb style varies slightly: load_, find_, forecast_, search_ are verbs while spending_by_ and top_ are noun phrases. Still, the pattern is mostly consistent.
Seven tools is well-scoped for a personal finance analysis server. Each tool covers a unique analytical angle and none feels redundant.
Core analysis workflows (load, categorize, top merchants, subscriptions, forecast, anomalies, search) are covered. Minor gaps like a dedicated list-all-transactions or income analysis exist but are workable via search.