Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/matematicsolutions/mcp-nsa/agents-mdgit clone --depth 1 https://github.com/matematicsolutions/mcp-nsaWrote 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.
[](https://agentmods.dev/instructions/matematicsolutions/mcp-nsa/agents-md)<a href="https://agentmods.dev/instructions/matematicsolutions/mcp-nsa/agents-md"><img src="https://agentmods.dev/badge/instructions/matematicsolutions/mcp-nsa/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00910 | $0.00910 |
| Opus 5 | $0.00455 | $0.00455 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
mcp-nsa 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - mcp-nsa
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 case law of the Polish administrative courts - Naczelny Sad Administracyjny / NSA (Supreme Administrative Court) + 16 Wojewodzkie Sady Administracyjne / WSA (regional administrative courts) - via the CBOSA database (orzeczenia.nsa.gov.pl).
This is where Polish GDPR / tax / administrative case law lives - practically every ruling of interest to compliance and tax law firms.
One of MateMatic's 5 Polish-law connectors (mcp-saos, mcp-nsa (this one), mcp-isap, mcp-krs, mcp-eu-sparql).
MateMatic context (HARD CONSTRAINTS)
The repo is run by MateMatic Solutions. The connector is trust infrastructure.
- Every tool call MUST return
structuredContent.citationswith: ruling title, canonical URL (CBOSA), court (NSA / WSA + location), date, case number. - Stateless - no caching of queries with PII.
- No text modification - a faithful copy from CBOSA.
- Rate limiting on the connector side - CBOSA has no official API; we scrape carefully, with respect for the court's resources.
MCP tools (tools contract)
| Tool | Key parameters | Returns |
|---|---|---|
search |
query, court? (NSA/WSA+city), date_from?, date_to? |
list of rulings + citations |
get_judgment |
judgment_id |
full ruling text + citations |
search_by_case |
case_number (case number) |
all rulings for a given case number |
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.
- 3d ago First seen · 74 lines · 910 tokens per session scan A b108b6dbd25e
mcp-nsa AGENTS.md is an instructions file published in the GitHub repository matematicsolutions/mcp-nsa (0 stars, last pushed 24d ago), licensed MIT. It adds 910 tokens to every session, about $0.0046 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.
Other instructions, from other repositories
mcp-saos AGENTS.md
Instructions for matematicsolutions/mcp-saos, covering agents.md - mcp-saos, project goal, matematic context (hard constraints), mcp tools (tools contract) and build and test.
mcp-legal-it CLAUDE.md
Instructions for capazme/mcp-legal-it, covering mcp-legal-it — project context, confini del progetto — leggere prima, stack, struttura and tool disponibili (33 moduli, 221 tool).
mcp-saos CLAUDE.md
Instructions for matematicsolutions/mcp-saos: This file exists for compatibility with Claude Code. The canonical instructions for AI agents working with this repo live in AGENTS.md - the agents.md standard (Linux Foundation / Agentic AI Foundation), supported by 20+ tools.
contract-ops-mcp AGENTS.md
AGENTS.md instructions for DrBaher/contract-ops-mcp, covering agents, discovery, output contract, safety boundaries (important) and typical loop.
ClauseKeeper clause-rules.instructions.md
Instructions for mityda/ClauseKeeper, covering clause rules and scanner instructions, rule structure, adding a jurisdiction or new legal regime safely and scanner engine expectations.
uk-legal-mcp CLAUDE.md
Instructions for paulieb89/uk-legal-mcp, covering claude.md — uk-legal-mcp, what this is, client ecosystems served, documentation index and commands.