What is ksef-mcp CLAUDE.md?

Project instructions for ksef-mcp, a software server that provides tools for Poland’s electronic invoicing system, including its build commands, structure, and available tool groups.

Building, running, and verifying the server; locating authentication, invoice, draft, sending, correction, and batch-processing code; and following its coding conventions.

They give a coding agent the project’s expected commands and organisation, reducing guesswork when changing or checking the code.

How gacabartosz/ksef-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gacabartosz/ksef-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/gacabartosz/ksef-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/gacabartosz/ksef-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gacabartosz/ksef-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/gacabartosz/ksef-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gacabartosz/ksef-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gacabartosz/ksef-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.

Your own site · 80×15

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

Per session 2,362 This file is loaded in full into every session.

When invoked 2,362 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	$0.02362	$0.02362
Opus 5	$0.01181	$0.01181
Sonnet 5	$0.00472	$0.00472
Haiku 4.5	$0.00236	$0.00236

Measured 10d ago against content hash 30b61cf2c4c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ksef-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 10d 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 · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — ksef-mcp

Build & Run

npm run build          # TypeScript compile + shebang injection
npm run dev            # Dev mode with tsx
npm start              # Run compiled dist/index.js

Verify tools after changes:

echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | node dist/index.js

Architecture

src/index.ts — MCP server entry point, Server + StdioServerTransport
src/mcp/registry.ts — Modular tool registry (registerTool, collectAll, dispatch)
src/mcp/auth-tools.ts — Auth tools: ksef_env_info, ksef_auth_init, ksef_auth_status, ksef_auth_terminate
src/mcp/query-tools.ts — Query tools: ksef_invoices_query, ksef_invoice_get, ksef_invoice_status, ksef_invoice_xml, ksef_upo_download
src/mcp/draft-tools.ts — Draft tools: ksef_draft_create, ksef_draft_get, ksef_draft_list, ksef_draft_update, ksef_draft_delete, ksef_draft_validate, ksef_draft_render_xml
src/mcp/send-tools.ts — Send tools: ksef_draft_lock, ksef_approval_request, ksef_approval_confirm, ksef_send_invoice, ksef_audit_log
src/mcp/correction-tools.ts — Correction tools: ksef_correction_create
src/mcp/batch-tools.ts — Batch tools: ksef_batch_open, ksef_batch_send_part, ksef_batch_close, ksef_batch_status
src/mcp/token-tools.ts — Token tools: ksef_token_generate, ksef_token_list, ksef_token_get, ksef_token_revoke
src/domain/draft.ts — Draft invoice CRUD, totals computation, status management (+ correction fields)
src/domain/validator.ts — FA(3) validation: NIP checksum, dates, VAT rates, totals
src/domain/xml-builder.ts — FA(3) XML builder using fast-xml-parser
src/domain/approval.ts — Two-phase approval gate: create, confirm, cancel, expiry (15min TTL)
src/domain/correction.ts — Invoice correction: cloneAsCorrection (clone sent invoice as new draft)
src/domain/audit.ts — Append-only JSONL audit log with hashed NIPs
src/infra/ksef/client.ts — HTTP client for KSeF API v2 (fetch + timeout + Bearer JWT auth)
src/infra/ksef/auth.ts — Auth flow v2: challenge → ksef-token → token/redeem → JWT access + refresh
src/infra/ksef/crypto.ts — RSA-OAEP, AES-256-CBC, SHA-256/Base64, public key certs
src/infra/ksef/session.ts — Online session: open, send encrypted invoices, close, status, UPO
src/infra/ksef/batch.ts — Batch session: open (pre-signed URLs), upload parts, close, status
src/infra/ksef/token-client.ts — KSeF token management: generate, list, get, revoke
src/utils/config.ts — Environment variables, base URLs (v2), data dirs
src/utils/logger.ts — JSON logging to stderr with secret masking
src/utils/errors.ts — toolResult/toolError helpers, KsefApiError class

Read the full file on GitHub · 148 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.

10d ago First seen · 148 lines · 2,362 tokens per session scan A 30b61cf2c4c1

Subscribe to this mod's changes

ksef-mcp CLAUDE.md is an instructions file published in the GitHub repository gacabartosz/ksef-mcp (4 stars, last pushed 6mo ago), licensed MIT. It adds 2,362 tokens to every session, about $0.0118 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

ksef-mcp: Instructions file for Claude Code