What is swift-tarot-mcp CLAUDE.md?

Repository instructions for a Swift server that lets compatible AI clients draw tarot cards and access the complete tarot deck through the Model Context Protocol, a standard way for AI tools to call external services.

Use them to build, run, format, lint, test, install, and troubleshoot the Swift tarot server, including its connection to an MCP client.

They give an AI coding assistant the project layout, commands, testing steps, and rules for keeping the server compatible with MCP. This reduces guesswork when building, testing, or checking the integration.

How junebash/swift-tarot-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to junebash/swift-tarot-mcp. 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/junebash/swift-tarot-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/junebash/swift-tarot-mcp

Made for: Claude Code.

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/junebash/swift-tarot-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/junebash/swift-tarot-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/junebash/swift-tarot-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/junebash/swift-tarot-mcp/claude-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/junebash/swift-tarot-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/junebash/swift-tarot-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 563 This file is loaded in full into every session.

When invoked 563 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	$0.00563	$0.00563
Opus 5.5	$0.00225	$0.00225
Sonnet 5.5	$0.00113	$0.00113
Haiku 4.5	$0.00056	$0.00056

Measured 2mo ago against content hash 6ddd44c85017, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

swift-tarot-mcp 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 2mo 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.

CLAUDE.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Overview

This is a Swift MCP (Model Context Protocol) server that provides tarot card reading functionality. The server exposes tools for drawing tarot cards and retrieving the full deck through the MCP protocol.

Key Commands

Development

just test - Run all tests
just build - Build debug version (includes linting)
just build release - Build release version
just build no-lint - Build without running SwiftLint
just run - Build and run debug version
just run release - Build and run release version
just install - Build release and install to /usr/local/bin/swift-tarot-MCP
just clean - Clean build artifacts
just lint - Run SwiftLint (pass --fix to auto-fix)
just format - Format code with swift-format
just check - Run all checks (test, format, lint)

Testing MCP Integration

Test locally: just run
Check Claude integration via MCP client logs

Common Issues & Solutions

MCP Tool Schema Issues

Critical: MCP tool schemas MUST follow JSON Schema Draft 7 specification exactly.

Incorrect (causes server crashes or disabled tools):

inputSchema: .object([
  "count": .object([...])
])

Correct (requires type and properties):

inputSchema: .object([
  "type": .string("object"),
  "properties": .object([
    "count": .object([...])
  ])
])

Symptoms of schema issues:

Server crashes during initialization
Tools show as disabled in Claude UI
tools/list requests fail

Debugging steps:

Check MCP client logs for schema validation errors
Verify all tool schemas have type: "object" at root level
Ensure properties are wrapped in properties object
Test with actual Claude client, not just local Swift tests

Installation Issues

Always rebuild and reinstall after schema changes: just install
Installed binary at /usr/local/bin/swift-tarot-MCP may be outdated
Local testing with just run may work while installed version fails

Read the full file on GitHub · 73 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.

2mo ago First seen · 73 lines · 563 tokens per session scan A 6ddd44c85017

Subscribe to this mod's changes

swift-tarot-mcp CLAUDE.md is an instructions file published in the GitHub repository junebash/swift-tarot-mcp (6 stars, last pushed 1y ago), licensed MIT. It adds 563 tokens to every session, about $0.0023 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.

Creative and media

swift-tarot-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
swift-tarot-mcp CLAUDE.mdjunebash/swift-tarot-mcp	Instructions file	6	1y ago	MIT	A	563	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	yesterday	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

swift-tarot-mcp: Instructions file for Claude Code