opencollective-hetzner-mcp: Instructions file for Codex

AGENTS.md

opencollective-hetzner-mcp AGENTS.md is an instructions file for Codex, OpenCode from theepicsaxguy/opencollective-hetzner-mcp. It costs 3,982 tokens per session, scanned A, original, Apache-2.0.

Project instructions for an OpenCollective MCP server, a tool that lets an agent work with OpenCollective’s online finance and community-management API. The project also covers retrieving Hetzner invoices and Cloudflare billing information.

In plain words
What is it for?
Use it when developing or maintaining the server that fetches hosting invoices and submits expenses to an OpenCollective collective, or manages collectives, expenses, members, and transactions.
Why use it?
It gives the agent the project’s architecture, design decisions, and API references so changes fit the existing server. The excerpt describes automated monthly bookkeeping as the main use case.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is theepicsaxguy/opencollective-hetzner-mcp's own configuration. It tells Codex and OpenCode how to work on opencollective-hetzner-mcp 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 opencollective-hetzner-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to theepicsaxguy/opencollective-hetzner-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/theepicsaxguy/opencollective-hetzner-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/theepicsaxguy/opencollective-hetzner-mcp

Made for: Codex, OpenCode.

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 opencollective-hetzner-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/theepicsaxguy/opencollective-hetzner-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/theepicsaxguy/opencollective-hetzner-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/theepicsaxguy/opencollective-hetzner-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/theepicsaxguy/opencollective-hetzner-mcp/agents-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 opencollective-hetzner-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/theepicsaxguy/opencollective-hetzner-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/theepicsaxguy/opencollective-hetzner-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,982 This file is loaded in full into every session.
When invoked 3,982 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.03982 $0.03982
Opus 5.5 $0.01593 $0.01593
Sonnet 5.5 $0.00796 $0.00796
Haiku 4.5 $0.00398 $0.00398

Measured 2mo ago against content hash 2e59ca7b4bb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

opencollective-hetzner-mcp AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST https://api.opencollective.com/graphql/v2 \
AGENTS.md · 394 lines

How it starts

The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenCollective MCP Server

A Model Context Protocol server that gives AI agents programmatic access to the OpenCollective GraphQL API v2, Hetzner Cloud invoices, and Cloudflare billing. Built with Python, FastMCP, and httpx.

The primary use case is automated monthly bookkeeping: fetching hosting invoices from Hetzner and Cloudflare, then submitting them as expenses to an OpenCollective collective -- but the server exposes the full range of OpenCollective operations so any agent can manage collectives, expenses, members, and transactions without manual intervention.


Architecture

src/opencollective_mcp/
  __init__.py              Package marker
  __main__.py              `python -m opencollective_mcp` entrypoint
  server.py                FastMCP server -- all 22 tools, input models, lifespan
  client.py                Async GraphQL client for OpenCollective API v2
  queries.py               GraphQL query/mutation strings (organized by domain)
  hetzner.py               Hetzner client wrapper (uses browser automation)
  hetzner_browser.py       Browser automation for Hetzner Accounts login and invoice retrieval
  cloudflare.py            Cloudflare billing client (uses REST API)

Design decisions

Separation of concerns. The GraphQL client (client.py) knows nothing about MCP. The query strings (queries.py) are plain constants. The Hetzner client (hetzner.py) is its own module. The server (server.py) wires them together through FastMCP tools. Any piece can be swapped, tested, or reused independently.

No hardcoded slugs or IDs. Every tool accepts the account slug / ID as a parameter. The server itself stores no state about which collective it operates on.

Authenticated and unauthenticated. Read-only OpenCollective queries (account info, public expenses, transactions, members) work without a token. Write operations and Hetzner calls require their respective tokens via environment variables.

Read the full file on GitHub · 394 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. 2mo ago First seen · 394 lines · 3,982 tokens per session scan A 2e59ca7b4bb7

Subscribe to this mod's changes

opencollective-hetzner-mcp AGENTS.md is an instructions file published in the GitHub repository theepicsaxguy/opencollective-hetzner-mcp (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,982 tokens to every session, about $0.0159 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

opencollective-hetzner-mcp AGENTS.md compared with instructions from other repositories

opencollective-hetzner-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
opencollective-hetzner-mcp AGENTS.mdtheepicsaxguy/opencollective-hetzner-mcpInstructions file14d agoApache-2.0A3,982Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode