bankstatemently
Official# bankstatemently/plugins
[](https://glama.ai/mcp/servers/bankstatemently/plugins)
Marketplace plugins for [Bankstatemently](https://bankstatemently.com) — convert bank statements.
## Install via Claude Code marketplace
```bash
/plugin marketplace add bankstatemently/plugins
/plugin install bankstatemently@bankstatemently
```
After installing, enable the plugin and paste your `bsk_live_...` key when prompted for `api_key`.
Get an API key at [bankstatemently.com/developer](https://bankstatemently.com/developer).
## Plugins
- **[bankstatemently](./bankstatemently/)** — MCP server for converting bank statements.
Convert PDFs, list statements, check credits, run benchmark evaluations.
TDQS
Scored across 16 tools
Most tools have clearly distinct responsibilities: ingestion (convert_statement, request_upload), retrieval (get_statement, list_statements), analysis (aggregate, group_by, top_n, compare, time_series), and management (rate_statement, dismiss_statement, categorize_statement). The six analytics tools share similar scope/metric language and could occasionally be confused, but their descriptions are explicit enough to disambiguate.
The statement lifecycle tools follow a consistent verb_noun pattern (convert_statement, get_statement, list_statements, dismiss_statement, rate_statement, categorize_statement). However, the analytics tools break this pattern with bare verbs and phrases like aggregate, compare, group_by, top_n, and time_series, making the overall naming convention mixed but still readable.
At 16 tools, the server is slightly above the ideal 3-15 range but each tool earns its place across ingestion, document management, analytics, transfers, credits, and benchmarking. The count feels justified for the domain breadth, though a few analytics tools could theoretically be consolidated.
The domain is well covered: conversion, upload, retrieval, listing, rating, categorization, dismissal, transaction queries, aggregations, transfer matching, credits, and benchmark evaluation are all present. Minor gaps exist, such as no permanent delete (dismiss only hides) and no dedicated account-list endpoint, but these are workable and not core dead ends.