unofficial-dinero-mcp-server: Instructions file for Claude Code

CLAUDE.md

unofficial-dinero-mcp-server CLAUDE.md is an instructions file for Claude Code from oddergaard/unofficial-dinero-mcp-server. It costs 1,052 tokens per session, scanned A, original, MIT.

A server that connects AI assistants to Dinero, an online accounting system, through the Model Context Protocol (MCP), a standard way for assistants to call external tools. It uses credentials supplied in each request and provides accounting-related access.

In plain words
What is it for?
Use it to run the Dinero MCP server locally or in Docker, connect clients to its /mcp endpoint, authenticate requests, and follow the project’s accounting-year and balance rules.
Why use it?
It lets an MCP-compatible assistant work with Dinero without keeping the accounting credentials in server environment variables.

Instructions file for Claude Code

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

This is oddergaard/unofficial-dinero-mcp-server's own configuration. It tells Claude Code how to work on unofficial-dinero-mcp-server 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 unofficial-dinero-mcp-server configures →

Reuse

Borrowing it

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

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 unofficial-dinero-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/oddergaard/unofficial-dinero-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/oddergaard/unofficial-dinero-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/oddergaard/unofficial-dinero-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/oddergaard/unofficial-dinero-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,052 This file is loaded in full into every session.
When invoked 1,052 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 $0.01052 $0.01052
Opus 5 $0.00526 $0.00526
Sonnet 5 $0.00210 $0.00210
Haiku 4.5 $0.00105 $0.00105

Measured 8d ago against content hash 034be4419082, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

unofficial-dinero-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 8d 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 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.

Commands

go mod tidy           # fetch dependencies / regenerate go.sum
go build ./...        # compile
go vet ./...          # static analysis
go test ./...         # run all tests
go run .              # run server locally (no env vars needed — credentials come from URL)

Docker:

go mod tidy && docker build -t dinero-mcp .

Architecture

Go HTTP server using mark3labs/mcp-go for the MCP protocol.

Transport: Streamable HTTP via server.NewStreamableHTTPServer(s, server.WithStateLess(true)). Clients connect to /mcp with credentials as URL query params.

Auth: Credentials come from URL params on every request — no server-side env vars needed for Dinero. The middleware in internal/auth/middleware.go reads clientId, clientSecret, apiKey, organizationId from the URL, exchanges them for a Dinero OAuth token (cached in memory), and injects a *dinero.Client into the request context.

Dinero auth: OAuth password grant via https://authz.dinero.dk/dineroapi/oauth/token. Bearer token is cached per credential hash with 2-min early expiry.

Package layout:

  • main.go — server startup, streamable HTTP wiring
  • internal/auth/middleware.go — credential injection from URL params, token cache
  • internal/dinero/auth.go — OAuth token exchange + in-memory cache
  • internal/dinero/client.go — HTTP client with all Dinero API methods
  • internal/tools/ — one file per domain (invoices, files, contacts, accounts); each exports a Register*(s) function
  • internal/tools/helpers.gostrArg, intArg, boolArg, boolPtr, ClientFromCtx

Tool pattern: Tools call ClientFromCtx(ctx) to get the per-request Dinero client. Errors are returned as mcp.NewToolResultError(...) so the MCP client sees them as tool failures rather than protocol errors.

Accounting Year Rules

Read the full file on GitHub · 78 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. 8d ago First seen · 78 lines · 1,052 tokens per session scan A 034be4419082

Subscribe to this mod's changes

unofficial-dinero-mcp-server CLAUDE.md is an instructions file published in the GitHub repository oddergaard/unofficial-dinero-mcp-server (5 stars, last pushed 6mo ago), licensed MIT. It adds 1,052 tokens to every session, about $0.0053 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

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

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