What is mcp-server-tochka-bank CLAUDE.md?

A set of project instructions for Claude Code, an AI coding assistant, while working on the Tochka Bank MCP server.

It helps Claude Code install the project, run its tests, follow the project’s development guidance, and understand its Python modules and Tochka Bank integration.

It gives the assistant the project’s required development rules, test commands, source layout, and bank API details in one place.

How dontsovcmc/mcp-server-tochka-bank configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dontsovcmc/mcp-server-tochka-bank. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dontsovcmc/mcp-server-tochka-bank/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/dontsovcmc/mcp-server-tochka-bank

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/dontsovcmc/mcp-server-tochka-bank/claude-md/github.svg)](https://agentmods.dev/instructions/dontsovcmc/mcp-server-tochka-bank/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/dontsovcmc/mcp-server-tochka-bank/claude-md"><img src="https://agentmods.dev/badge/instructions/dontsovcmc/mcp-server-tochka-bank/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/dontsovcmc/mcp-server-tochka-bank/claude-md"><img src="https://agentmods.dev/badge/instructions/dontsovcmc/mcp-server-tochka-bank/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,637 This file is loaded in full into every session.

When invoked 1,637 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01637	$0.01637
Opus 5	$0.00818	$0.00818
Sonnet 5	$0.00327	$0.00327
Haiku 4.5	$0.00164	$0.00164

Measured 9d ago against content hash a9c12165ec75, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-server-tochka-bank CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Разработка

CRITICAL: Все правила разработки описаны в development.md. Всегда следовать им при любых изменениях кода, тестов и документации.

Запуск из исходников

pip install -e ".[test]"

Запуск тестов

pytest tests/ -v

Тесты мокают API Точки — TOCHKA_TOKEN не нужен. Все тесты проходят локально без доступа к реальному банку.

CI

GitHub Actions: .github/workflows/test.yml, runs-on: self-hosted. Токен не требуется.

Структура

src/mcp_server_tochka_bank/
├── __init__.py          # main(), версия
├── __main__.py          # python -m entry point
├── server.py            # FastMCP, 45 tools
├── tochka_api.py        # HTTP-клиент API Точки (43 метода)
├── cli.py               # CLI-интерфейс (37 команд)
├── models.py            # Pydantic-модели (для тестов)
├── goods.py             # локальный справочник товаров
└── invoice_tracker.py   # отслеживание оплаты счетов

API Точки

Документация: https://developers.tochka.com/docs/tochka-api/
Swagger: https://enter.tochka.com/doc/openapi/swagger.json
Base URL: https://enter.tochka.com/uapi
Авторизация: Authorization: Bearer <JWT>

Отслеживание оплаты счетов

При работе с MCP-сервером Точки соблюдай следующий сценарий:

После выставления счёта (tochka_invoice): счёт автоматически добавляется в отслеживание с document_id. Предложи запустить /loop 60m tochka_check_invoices если loop ещё не запущен.
"Отследи счёт 146": если счёт уже в трекере (создан через MCP) — запустить loop. Если нет — спросить ИНН плательщика и сумму, добавить через tochka_track_invoice, запустить loop.
При старте сессии: вызови tochka_pending_invoices. Если есть неоплаченные счета — сообщи список и автоматически запусти /loop 60m tochka_check_invoices.
После проверки (tochka_check_invoices): если найдены оплаченные счета — сообщи пользователю какие счета оплачены (кем, на какую сумму). Если все оплачены — останови loop.

Read the full file on GitHub · 117 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 117 lines · 1,637 tokens per session scan A a9c12165ec75

Subscribe to this mod's changes

mcp-server-tochka-bank CLAUDE.md is an instructions file published in the GitHub repository dontsovcmc/mcp-server-tochka-bank (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,637 tokens to every session, about $0.0082 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-server-tochka-bank: Instructions file for Claude Code