agentmods.dev

invoicexml-mcp AGENTS.md

Repository instructions for InvoiceXML MCP, a .NET server that lets AI agents work with electronic invoices through the InvoiceXML API. It covers supported invoice formats, commands, architecture, and rules that must remain intact.

In plain words
What is it for?
Use it when building, testing, running, or modifying the server, including invoice creation, validation, rendering, data extraction, embedding, and format conversion.
Why use it?
It gives coding agents the project context they need before changing the code. This helps them preserve important behavior across self-hosted API-key and hosted OAuth deployments.

Instructions file for CodexOpenCode

5 1mo ago A scan 1,336 tokens original MIT
View the source file InvoiceXML/invoicexml-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/invoicexml/invoicexml-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/InvoiceXML/invoicexml-mcp

Made for: Codex, OpenCode.

Per session 1,336 This file is loaded in full into every session.
When invoked 1,336 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01336 $0.01336
Opus 5 $0.00668 $0.00668
Sonnet 5 $0.00267 $0.00267
Haiku 4.5 $0.00134 $0.00134

Measured 2d ago against content hash 677c9cbd367e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

invoicexml-mcp AGENTS.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 2d 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.

AGENTS.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Context for AI coding agents (and humans) working in this repository. Canonical prose lives in README.md and CONTRIBUTING.md; this file is the high-signal summary.

Note: GEMINI.md is a different thing. It is the end-user context for the hosted MCP server, referenced by gemini-extension.json. Do not put repo build or contributor instructions there.

What this is

A Model Context Protocol server (C# / .NET 10) that exposes the InvoiceXML API to AI agents: create, validate, render, extract, embed, and convert e-invoices across Factur-X, ZUGFeRD, XRechnung, UBL / CII, and Peppol BIS Billing 3.0.

One codebase, two deployment shapes, selected at startup by Mcp:AuthMode: ApiKey (self-hosted, single API key) or OAuth (hosted, OAuth 2.1 + DCR against invoicexml.com). The repo is platform-independent: it knows nothing about where or how it is hosted.

Commands

dotnet build                                   # whole solution (warnings are errors)
dotnet test                                    # all tests (xUnit)
dotnet test tests/InvoiceXml.Mcp.Core.Tests/InvoiceXml.Mcp.Core.Tests.csproj
dotnet run --project src/InvoiceXml.Mcp.Host   # run the host locally

Requires a .NET 10 SDK (global.json floor is 10.0.100, rolls forward to the latest 10.0.x). To run, supply an API key first, kept outside the repo: dotnet user-secrets --project src/InvoiceXml.Mcp.Host set "Mcp:ApiKey:Value" "<key>".

Local endpoints: GET / welcome page, POST / MCP endpoint, GET /health.

Architecture

InvoiceXml.Mcp.Core  --ProjectReference-->  InvoiceXml.Mcp.Host
(SDK: client + tools)                       (the deployable ASP.NET Core app)
  • Core is a transport- and auth-agnostic SDK: IInvoiceXmlClient + HttpInvoiceXmlClient, the DTOs/enums, and the [McpServerTool] classes. It consumes an HttpClient from IHttpClientFactory and never sees credentials.
  • Host reads Mcp:AuthMode and attaches the matching auth as an HttpClient DelegatingHandler via AddHostAuth(...). That handler seam is the whole reason one codebase serves both modes.

Read the full file on GitHub · 107 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. 2d ago First seen · 107 lines · 1,336 tokens per session scan A 677c9cbd367e

Subscribe to this mod's changes

invoicexml-mcp AGENTS.md is an instructions file published in the GitHub repository InvoiceXML/invoicexml-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,336 tokens to every session, about $0.0067 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.

Backend and APIsData and AITestinggemini-cli-extension
Related

Other instructions, from other repositories

notfair-plugin AGENTS.md

AGENTS.md instructions for nowork-studio/notfair-plugin, covering notfair — skill resolver for ai agents, how to use this file, seo, paid ads and analytics.

nowork-studio/notfair-plugin · 2,291 tokens

Agentkey AGENTS.md

Instructions for chainbase-labs/Agentkey, covering agents.md, what this repo is, directory structure, key commands and test a local edit against every detected agent.

chainbase-labs/Agentkey · 3,953 tokens

domscribe CLAUDE.md

Instructions for patchorbit/domscribe, covering claude.md, what is domscribe?, how to work on this codebase, commands and install dependencies (pnpm, not npm).

patchorbit/domscribe · 1,823 tokens

mcp-server-tauri GEMINI.md

Instructions for hypothesi/mcp-server-tauri, covering tauri mcp cli, core workflow, critical failure modes and skill.

hypothesi/mcp-server-tauri · 226 tokens

bookstack-mcp CLAUDE.md

Instructions for ttpears/bookstack-mcp, covering claude.md, project overview, build & development commands, architecture and configuration.

ttpears/bookstack-mcp · 1,443 tokens

logic-lens GEMINI.md

Instructions for hyhmrright/logic-lens, covering logic-lens — developer guide (gemini cli), invoking skills, installation, project layout and key conventions.

hyhmrright/logic-lens · 285 tokens