e-arveldaja-mcp: Instructions file for Claude Code

CLAUDE.md

e-arveldaja-mcp CLAUDE.md is an instructions file for Claude Code from iseppo/e-arveldaja-mcp. It costs 9,847 tokens per session, scanned A, original, Apache-2.0.

Instructions for an MCP server that connects coding agents to Estonia’s e-arveldaja, the RIK e-Financials accounting service. It explains setup, credentials, accounting knowledge storage, and connections to multiple companies.

In plain words
What is it for?
Setting up the server, choosing between its tool profiles, loading API keys, connecting several companies, and locating stored accounting guidance.
Why use it?
It gives the agent the information needed to start the accounting connection correctly and avoid using the wrong credentials or company account.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is iseppo/e-arveldaja-mcp's own configuration. It tells Claude Code how to work on e-arveldaja-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything e-arveldaja-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to iseppo/e-arveldaja-mcp. 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/iseppo/e-arveldaja-mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/iseppo/e-arveldaja-mcp

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.

agentmods badge for e-arveldaja-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/iseppo/e-arveldaja-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/iseppo/e-arveldaja-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/iseppo/e-arveldaja-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iseppo/e-arveldaja-mcp/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.

agentmods 80×15 button for e-arveldaja-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/iseppo/e-arveldaja-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iseppo/e-arveldaja-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,847 This file is loaded in full into every session.
When invoked 9,847 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.09847 $0.09847
Opus 5 $0.04924 $0.04924
Sonnet 5 $0.01969 $0.01969
Haiku 4.5 $0.00985 $0.00985

Measured 9d ago against content hash 1b47908231c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

e-arveldaja-mcp 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 · 542 lines

How it starts

The opening of the file, as written. The whole thing — 542 lines — stays where its author put it; the contents beside it link to each section on GitHub.

e-arveldaja MCP Server

TypeScript MCP server for the Estonian e-arveldaja (RIK e-Financials) REST API. 127 tools by default on the compatibility-preserving standard profile; opt-in guided / guided-sales expose 19 / 20 tools, and full exposes all 147. There are 16 workflow prompts and 15 resources across 12 modules. Supports multiple companies/accounts.

Quick Start

npm run build          # tsc -> dist/
npm run start          # node dist/index.js (stdio transport)
npm run dev            # tsx src/index.ts (development)

Credentials

All apikey*.txt files are scanned from the working directory (where the server is launched). Multiple files = multiple connections (companies).

Credentials are loaded in this priority order (see src/config.ts):

  1. EARVELDAJA_API_KEY_FILE env var pointing to a specific file
  2. Environment variables: EARVELDAJA_API_KEY_ID, EARVELDAJA_API_PUBLIC_VALUE, EARVELDAJA_API_PASSWORD
  3. .env files — local working directory first, then global config directory (~/.config/e-arveldaja-mcp)
  4. apikey*.txt files — scanned from the working directory (import source, not long-term store)

The apikey.txt format:

ApiKey ID: <key_id>
ApiKey public value: <public_value>
Password: <password>

Set EARVELDAJA_SERVER=demo for the demo API (default: live).

Multi-account (multiple companies)

Place multiple apikey*.txt files (e.g. apikey.txt, apikey (1).txt) next to the project. Use list_connections to see all available accounts and switch_connection to switch between them. Switching clears all cached data to prevent cross-company data leaks.

NEVER commit .env or apikey.txt to git. The .gitignore is configured to exclude them.

Accounting-knowledge storage location

Company-specific booking rules (see src/accounting-rules.ts) are stored as an Open Knowledge Format bundle. Two env vars control where it lives:

  • EARVELDAJA_RULES_DIR — points to the bundle directory (OKF: one concept per .md file + reserved index.md/log.md). This is the recommended override. In this (default) bundle mode, a legacy accounting-rules.md found in the bundle's parent dir is migrated non-destructively into the bundle on first write.
  • EARVELDAJA_RULES_FILE — opts into legacy single-file mode: rules stay in that one accounting-rules.md (no bundle, no migration). For people who want the old behaviour byte-for-byte.

Read the full file on GitHub · 542 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.

  1. 9d ago First seen · 542 lines · 9,847 tokens per session scan A 1b47908231c9

Subscribe to this mod's changes

e-arveldaja-mcp CLAUDE.md is an instructions file published in the GitHub repository iseppo/e-arveldaja-mcp (34 stars, last pushed 6d ago), licensed Apache-2.0. It adds 9,847 tokens to every session, about $0.0492 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 2026-08-30.

Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens