Borrowing it
Nothing to install: this file belongs to matematicsolutions/mcp-saos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/matematicsolutions/mcp-saos/main/AGENTS.mdgit clone --depth 1 https://github.com/matematicsolutions/mcp-saosWrote 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-saos/agents-md)<a href="https://agentmods.dev/instructions/matematicsolutions/mcp-saos/agents-md"><img src="https://agentmods.dev/badge/instructions/matematicsolutions/mcp-saos/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.
<a href="https://agentmods.dev/instructions/matematicsolutions/mcp-saos/agents-md"><img src="https://agentmods.dev/badge/instructions/matematicsolutions/mcp-saos/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01243 | $0.01243 |
| Opus 5.5 | $0.00497 | $0.00497 |
| Sonnet 5.5 | $0.00249 | $0.00249 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade C, and why
mcp-saos AGENTS.md scanned grade C with 1 finding 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
- **Do NOT add tools that send user data to external APIs** other than SAOS. The connector must be **single-source** (SAOS); every additional source = a separate MCP repo. How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - mcp-saos
An agents.md standard file (Linux Foundation / Agentic AI Foundation) - the 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 case law of the Polish common courts, the Sad Najwyzszy (Supreme Court), the Trybunal Konstytucyjny (Constitutional Tribunal), and the KIO (National Appeal Chamber) - via the public SAOS (System Analizy Orzeczen Sadowych - the courts' public case-law database) API, https://saos.org.pl.
One of MateMatic's 5 Polish-law connectors: mcp-saos (this one), mcp-nsa, mcp-isap, mcp-krs, mcp-eu-sparql.
The connector plugs in via mcp-servers.json in any protocol-compliant client (Claude Code, Patron, Cursor, Codex, Continue, etc.).
MateMatic context (HARD CONSTRAINTS)
The repo is run by MateMatic Solutions. The connector is trust infrastructure - it serves any LegalTech product that needs citations from Polish case law, in any jurisdiction.
- Every tool call MUST return
structuredContent.citationswith: judgment title, canonical URL (SAOS), court, date, case number. This is the product contract. - No caching of client data - the connector is stateless and does not log queries.
- No content modification - we return exactly what the SAOS API returns, with no "enhancement" / summarization. Modification = loss of evidentiary value.
MCP tools (tools contract)
| Tool | Key parameters | Returns |
|---|---|---|
search |
query, court_type?, date_from?, date_to? |
list of judgments with metadata + citations |
get_judgment |
judgment_id |
full judgment text + metadata + citations |
search_by_case |
case_number (case signature) |
all judgments 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.
- 14d ago Changed · +2 lines · +131 tokens per session 12a705a14d9c
- 1mo ago First seen · 79 lines · 1,112 tokens per session scan C a1c1982034ca
mcp-saos AGENTS.md is an instructions file published in the GitHub repository matematicsolutions/mcp-saos (2 stars, last pushed 14d ago), licensed MIT. It adds 1,243 tokens to every session, about $0.0050 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.