What is mcp-krs AGENTS.md?

The main instruction file for AI coding tools in a repository that provides an MCP server for Poland's National Court Register. MCP is a standard way for AI assistants to call external tools.

It guides work on the KRS connector, including its official Ministry of Justice API, stateless behavior, historical data handling, GDPR considerations, and tool response requirements.

It gives coding agents the project's purpose, legal and data constraints, required citation format, and build and test rules in one canonical place.

How matematicsolutions/mcp-krs configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to matematicsolutions/mcp-krs. 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/matematicsolutions/mcp-krs/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/matematicsolutions/mcp-krs

Made for: Codex, OpenCode.

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/matematicsolutions/mcp-krs/agents-md/github.svg)](https://agentmods.dev/instructions/matematicsolutions/mcp-krs/agents-md)

Your own site

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

Per session 1,177 This file is loaded in full into every session.

When invoked 1,177 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	$0.01177	$0.01177
Opus 5.5	$0.00471	$0.00471
Sonnet 5.5	$0.00235	$0.00235
Haiku 4.5	$0.00118	$0.00118

Measured 14d ago against content hash c40864cdb670, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-krs AGENTS.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 14d 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.

AGENTS.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - mcp-krs

An agents.md standard file (Linux Foundation / Agentic AI Foundation) - canonical instructions for AI agents working with this repository. Read natively by Cursor, Codex (OpenAI), Jules (Google), Devin / Windsurf, Aider, Amp, Factory, GitHub Copilot.

Project goal

An MCP (Model Context Protocol) server for the Krajowy Rejestr Sadowy / KRS (National Court Register) - via the official, free API of the Ministerstwo Sprawiedliwosci (Ministry of Justice) (api.krs.ms.gov.pl).

One of the 5 MateMatic Polish-law connectors (mcp-saos, mcp-nsa, mcp-isap, mcp-krs (this one), mcp-eu-sparql).

MateMatic context (HARD CONSTRAINTS)

The repo is maintained by MateMatic Solutions.

KRS data is public but GDPR applies when combining it with other data (board = natural persons).
Every tool call MUST return structuredContent.citations with: the KRS number, extract date, canonical URL (krs.ms.gov.pl).
Stateless - no cache.
Current register or full historical only - every extract has a snapshot date that must be in the citation. An outdated KRS = risk of a factual error.

MCP tools (tools contract)

Tool	Key parameters	Returns
`get_entity`	`krs`, `rejestr` (P/S)	current extract: name, NIP, REGON, status, share capital + citations
`get_entity_full`	`krs`, `rejestr`	full historical extract (all changes since registration)
`get_board`	`krs`, `rejestr`	current board + supervisory bodies (note: PII of natural persons)

Full description: src/index.ts + README.md.

Build and test

npm install        # Node 20+
npm run build      # tsc -> dist/
npm start          # node dist/index.js
npm run dev        # ts-node src/index.ts
npm test           # drift + unit + E2E on a local KRS stub (offline; needs build)
npm run test:package  # npm pack gate: runtime files present in the package
npm run smoke      # live KRS API, every tool from tools/list (not part of release)

Read the full file on GitHub · 78 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.

14d ago Changed · +5 lines · +225 tokens per session c40864cdb670
1mo ago First seen · 73 lines · 952 tokens per session scan A 00170f28f191

Subscribe to this mod's changes

mcp-krs AGENTS.md is an instructions file published in the GitHub repository matematicsolutions/mcp-krs (1 stars, last pushed 14d ago), licensed MIT. It adds 1,177 tokens to every session, about $0.0047 per session on Opus 5.5. 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.

ai-agent company-registry krs legal-tech mcp model-context-protocol

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 · 9,715 tokens

mcp-krs: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md - mcp-krs

Project goal

MateMatic context (HARD CONSTRAINTS)

MCP tools (tools contract)

Build and test

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

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

langchain AGENTS.md

vscode copilot-instructions.md

vscode model-prompts.instructions.md