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-eureka/agents-mdgit clone --depth 1 https://github.com/matematicsolutions/mcp-eurekaWhat 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 | $0.00884 | $0.00884 |
| Opus 5 | $0.00442 | $0.00442 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade C, and why
mcp-eureka 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 2d 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 EUREKA. The connector is **single-source**; every additional source = a separate MCP repo (fleet convention). How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - mcp-eureka
An agents.md standard file (Linux Foundation / Agentic AI Foundation) - canonical instructions for AI agents working with this repository.
Project goal
An MCP (Model Context Protocol) server for Polish tax interpretations and the practice of the Ministerstwo Finansow / MF (Ministry of Finance) - via the public JSON API of the EUREKA system (eureka.mf.gov.pl). 550,000+ documents, including 517,000+ individual KIS tax interpretations.
One of the MateMatic Polish-law connectors: mcp-saos, mcp-nsa, mcp-eureka (this one), mcp-isap, mcp-krs, kio-orzeczenia-mcp.
MateMatic context (HARD CONSTRAINTS)
The repo is run by MateMatic Solutions. The connector is trust infrastructure.
- Every tool call MUST return
structuredContent.citationswith: title, canonical URL (eureka.mf.gov.pl/informacje/podglad/{id}), signature, issue date. - Stateless - no caching of queries containing PII (the only in-memory cache: the public category dictionary).
- No content modification - we return verbatim from EUREKA.
- Throttling - max 2 req/s against MF infrastructure, User-Agent carrying the repo address.
What NOT to do (hard rules)
- Do NOT add tools that send user data to external APIs other than EUREKA. The connector is single-source; every additional source = a separate MCP repo (fleet convention).
- Do NOT modify returned content - the data is primary, with evidentiary value.
- Do NOT guess the meaning of dictionary ids (PRZEPISY/ZAGADNIENIA/SLOWA_KLUCZOWE in the full document) - refer to the source page.
- No breaking changes without a MAJOR bump + a CHANGELOG entry.
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.
- 2d ago First seen · 58 lines · 884 tokens per session scan C 6e77aaf0c091
mcp-eureka AGENTS.md is an instructions file published in the GitHub repository matematicsolutions/mcp-eureka (0 stars, last pushed 1mo ago), licensed MIT. It adds 884 tokens to every session, about $0.0044 per session on Opus 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.