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/j4th/mtg-mcp-server/claude-mdgit clone --depth 1 https://github.com/j4th/mtg-mcp-serverWrote 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/j4th/mtg-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/j4th/mtg-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/j4th/mtg-mcp-server/claude-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 | $0.03716 | $0.03716 |
| Opus 5 | $0.01858 | $0.01858 |
| Sonnet 5 | $0.00743 | $0.00743 |
| Haiku 4.5 | $0.00372 | $0.00372 |
Grade A, and why
mtg-mcp-server 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 5d 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MTG MCP Server
Unified MCP server providing Magic: The Gathering data to AI assistants. Composes Scryfall, Commander Spellbook, 17Lands, and EDHREC into one server using FastMCP 3.x's provider/mount architecture.
Stack
Python 3.12+ · FastMCP 3.2.x · httpx · Pydantic v2 · structlog Tooling: mise · uv · ruff · ty · pytest · respx
Prerequisites: mise must be installed. Then mise install gets everything else.
Commands
mise run setup # Install deps, create venv
mise run check # Quality gate: lint + typecheck + all tests except live
mise run check:quick # Fast gate: lint + typecheck + only tests affected by recent changes
mise run check:full # Complete gate: lint + typecheck + all tests INCLUDING live
mise run test # All tests except live, with coverage
mise run test:quick # Only tests affected by recent changes (fastest iteration)
mise run test:unit # Unit tests only (services + providers)
mise run test:integration # Integration tests (fixture-mocked, cross-component)
mise run test:live # Live smoke tests (real server + real APIs, ~60s)
mise run lint # ruff check + ruff format --check
mise run typecheck # ty check
mise run dev # fastmcp dev inspector (MCP Inspector on :6274)
mise run serve # Run server via stdio
mise run fix # Auto-fix lint and format issues
Testing strategy
Four test tiers, ordered by speed. Use the fastest tier that covers your change:
| Tier | Command | Speed | When to use |
|---|---|---|---|
| Quick | mise run test:quick |
~5s* | Active iteration — only runs tests affected by your changes (pytest-testmon) |
| Integration | mise run test:integration |
~2s | Cross-component verification — full orchestrator with fixture-mocked backends |
| Unit | mise run test:unit |
~2.5min | Focused component testing — services + providers only |
| Live | mise run test:live |
~1-2min | Real-world smoke test — starts real server, hits real APIs |
| Fast gate | mise run check:quick |
~10s* | Quick validation — lint + typecheck + affected tests only |
| Quality gate | mise run check |
~3min | Before commits — lint + typecheck + all tests except live |
| Complete gate | mise run check:full |
~4-5min | Maximum confidence — full gate + live smoke tests. CI runs this on PRs |
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.
- 5d ago First seen · 186 lines · 3,716 tokens per session scan A 544a09d0aee3
mtg-mcp-server CLAUDE.md is an instructions file published in the GitHub repository j4th/mtg-mcp-server (17 stars, last pushed 2mo ago), licensed MIT. It adds 3,716 tokens to every session, about $0.0186 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 2026-08-30.
Other instructions, from other repositories
MagicAIBuilder AGENTS.md
AGENTS.md instructions for KaelSensei/MagicAIBuilder, covering magicaibuilder — coding standards, language & runtime, type safety — non-negotiable rules, no type assertions (as) and no non-null assertions (!).
MagicAIBuilder CLAUDE.md
Claude Code instructions for KaelSensei/MagicAIBuilder, covering magicaibuilder — project instructions, skills — load these for the right job, project-specific rules (not covered by any skill), branch flow — dev → staging → main and documentation discipline.
RivalSearchMCP AGENTS.md
AGENTS.md instructions for damionrashford/RivalSearchMCP, covering agents.md, project overview, development commands, setup & running and install dependencies.
markdown-vault-mcp AGENTS.md
AGENTS.md instructions for pvliesdonk/markdown-vault-mcp, covering markdown vault mcp, design, project structure, conventions and skills.
cpf-validador CLAUDE.md
Claude Code instructions for opastorello/cpf-validador, covering claude.md, comandos, rodar localmente (fastapi + fastmcp na porta 8000), docker (porta 8002 conforme docker-compose.yaml) and arquitetura.
substack-gateway-oss CLAUDE.md
Claude Code instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.