What is luno-mcp CLAUDE.md?

Development instructions for Luno MCP, a Go-based MCP server that wraps the Luno cryptocurrency exchange API. They cover commands, architecture, code style, testing, and pre-commit checks.

Use them to build and test the server, run its different connection modes, work on API tools, regenerate test helpers, and prepare commits.

They make the project’s build, test, formatting, and validation process clear so changes can be checked consistently.

How luno/luno-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to luno/luno-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/luno/luno-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/luno/luno-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/luno/luno-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/luno/luno-mcp/claude-md)

Your own site

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

Per session 1,393 This file is loaded in full into every session.

When invoked 1,393 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	$0.01393	$0.01393
Opus 5	$0.00696	$0.00696
Sonnet 5	$0.00279	$0.00279
Haiku 4.5	$0.00139	$0.00139

Measured 9d ago against content hash 86c22c85b2ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

luno-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 9d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 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.

Development commands

make build - Build the luno-mcp binary into the repo root
make test - Run all tests (go test ./...)
go test ./internal/tools/... -run TestHandleGetBalances - Run a single test or package
make run-stdio / make run-sse / make run-streamable-http - Run server with each transport
make install - Install binary to $GOBIN
make pre-commit - Install pre-commit hooks (requires gofumpt installed separately: go install mvdan.cc/gofumpt@latest)
go tool mockery - Regenerate mocks (mockery is declared as a Go tool in go.mod, not invoked standalone). Config is in .mockery.yml.

Pre-commit runs go-vet-mod, go-imports, gofumpt, go-mod-tidy-repo, go-test-repo-mod, plus YAML/whitespace/EOF checks and a script-test for claude-desktop-install.sh. These run on every commit - run pre-commit run --all-files to validate before pushing.

Architecture

This is an MCP server wrapping the Luno crypto exchange API. Three layers matter:

sdk/luno_client.go defines the LunoClient interface that all tool/resource handlers depend on. The real *luno.Client satisfies it via a compile-time check; sdk/mock_luno_client_gen.go is the mockery-generated test double. Never call luno.Client methods directly from internal/ - go through the interface so tests can substitute the mock.

internal/config owns Config, which carries the LunoClient, an IsAuthenticated flag, and AllowWriteOperations. config.Load() decides authentication mode by inspecting env vars at startup - if LUNO_API_KEY_ID/LUNO_API_SECRET are absent, the server runs in unauthenticated mode and authenticated tools (get_balances, list_orders, etc.) return ErrAPICredentialsRequired rather than failing at registration time. CLI --allow-write-operations overrides the env var.

internal/server/server.go wires everything: NewMCPServer registers resources and tools, then ServeStdio / ServeSSE / ServeStreamableHTTP start the chosen transport. Key design choice in registerTools: write tools (create_order, cancel_order) are always registered with the server, but when AllowWriteOperations=false they are bound to HandleWriteOperationDisabled() instead of their real handlers. This means MCP clients can see the tools exist and discover how to enable them, rather than the tools silently disappearing. Don't change this pattern when adding new write tools.

Read the full file on GitHub · 55 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.

9d ago First seen · 55 lines · 1,393 tokens per session scan A 86c22c85b2ab

Subscribe to this mod's changes

luno-mcp CLAUDE.md is an instructions file published in the GitHub repository luno/luno-mcp (25 stars, last pushed 12d ago), licensed MIT. It adds 1,393 tokens to every session, about $0.0070 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.

arbitrage cryptocurrency mcp trading

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

luno-mcp: Instructions file for Claude Code