mcp-kraken: Instructions file for Claude Code

CLAUDE.md

mcp-kraken CLAUDE.md is an instructions file for Claude Code from XavierBeheydt/mcp-kraken. It costs 1,688 tokens per session, scanned A, original, MIT.

A project instruction file for an MCP server that exposes Kraken's spot-trading REST API over HTTP. MCP is a standard way for tools to be used by AI agents.

In plain words
What is it for?
Use it when working on the server, bearer-token CLI, SQLite token store, tests, packaging, or container setup.
Why use it?
It gives coding agents the project's architecture, supported technologies, boundaries, and normal commands before they change code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is XavierBeheydt/mcp-kraken's own configuration. It tells Claude Code how to work on mcp-kraken itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-kraken configures →

Reuse

Borrowing it

Nothing to install: this file belongs to XavierBeheydt/mcp-kraken. 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/XavierBeheydt/mcp-kraken/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/XavierBeheydt/mcp-kraken

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.

agentmods badge for mcp-kraken CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xavierbeheydt/mcp-kraken/claude-md/github.svg)](https://agentmods.dev/instructions/xavierbeheydt/mcp-kraken/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/xavierbeheydt/mcp-kraken/claude-md"><img src="https://agentmods.dev/badge/instructions/xavierbeheydt/mcp-kraken/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.

agentmods 80×15 button for mcp-kraken CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/xavierbeheydt/mcp-kraken/claude-md"><img src="https://agentmods.dev/badge/instructions/xavierbeheydt/mcp-kraken/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,688 This file is loaded in full into every session.
When invoked 1,688 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01688 $0.01688
Opus 5 $0.00844 $0.00844
Sonnet 5 $0.00338 $0.00338
Haiku 4.5 $0.00169 $0.00169

Measured 10d ago against content hash 54bb69576fdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-kraken 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 10d 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 · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project guidance — mcp-kraken

This file is the canonical project brief for Claude (and humans). Read it before making changes; keep it under 300 lines.

What this project is

An MCP server that wraps the Kraken Spot REST API and exposes it over HTTP with bearer-token authentication, plus a CLI for managing those bearer tokens. Built on FastMCP. Single process, stateless beyond a SQLite token store.

WebSocket v2 and FIX are explicitly out of scope for v1 — they live in TODO.md.

Stack

  • Python 3.12+ (CI matrix tests 3.12 and 3.13)
  • Dependency manager: uv (uv add, uv sync, uv run)
  • Build backend: hatchling + hatch-vcs — version is derived from the git tag (vX.Y.ZX.Y.Z). Never hand-edit a version field.
  • HTTP framework: FastMCP (streamable HTTP transport)
  • HTTP client: httpx (async)
  • Validation/config: pydantic + pydantic-settings
  • CLI: typer + rich
  • Tests: pytest + pytest-asyncio + respx (httpx mocks)
  • Quality: ruff (lint + format), mypy (strict)
  • Container: multi-stage Dockerfile, non-root uid 10001, distroless-style runtime

Layout

src/mcp_kraken/
├── __init__.py __main__.py cli.py config.py logging.py server.py
├── auth/          # bearer-token store (SQLite), FastMCP TokenVerifier
├── kraken/        # async REST client, HMAC signing, errors, permission map
└── tools/         # MCP tool registrations, one module per Kraken category
tests/             # pytest; uses respx to mock httpx
docker/            # Dockerfile (build context is repo root)
.github/workflows/ # test.yml, dev-publish.yml, release.yml

Source files live at src/mcp_kraken/ (src layout). Docker files in docker/.

Common commands

just sync          # uv sync --all-extras --dev
just check         # ruff + format-check + mypy + pytest (= what CI runs)
just test          # pytest
just fix           # auto-fix lint + reformat
just serve         # plain HTTP on :8765/mcp
just serve-https   # HTTPS using ./certs/{key,cert}.pem
just serve-stdio   # stdio transport (for local Claude Desktop / uvx)
just cert-local    # mkcert: generates locally-trusted TLS certs
just docker-build  # local image build (tagged :dev)

Read the full file on GitHub · 150 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.

  1. 10d ago First seen · 150 lines · 1,688 tokens per session scan A 54bb69576fdc

Subscribe to this mod's changes

mcp-kraken CLAUDE.md is an instructions file published in the GitHub repository XavierBeheydt/mcp-kraken (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,688 tokens to every session, about $0.0084 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.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens