What is ge-app-mcp AGENTS.md?

A set of AGENTS.md instructions for developing and maintaining a Gemini Enterprise MCP server. AGENTS.md is a project guide that tells coding agents how a codebase should be changed and tested.

For guiding work on the server's tools, permissions, Google Cloud API safeguards, architecture, and testing workflow.

It gives the agent the repository's architecture, safety rules, editing process, and verification requirements before code changes are made.

How miticojo/ge-app-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to miticojo/ge-app-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/miticojo/ge-app-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/miticojo/ge-app-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/miticojo/ge-app-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/miticojo/ge-app-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/miticojo/ge-app-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/miticojo/ge-app-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.

Your own site · 80×15

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

Per session 5,218 This file is loaded in full into every session.

When invoked 5,218 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	$0.05218	$0.05218
Opus 5.5	$0.02087	$0.02087
Sonnet 5.5	$0.01044	$0.01044
Haiku 4.5	$0.00522	$0.00522

Measured 13d ago against content hash 0a92c2f04606, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ge-app-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 13d 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 · 311 lines

How it starts

The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🤖 AI Coding Agent Developer Guide (AGENTS.md)

This document is the authoritative developer guide and instruction manual for any AI Coding Agent (such as Cursor, Windsurf, or custom agentic workflows) tasked with modifying, extending, or maintaining this Gemini Enterprise MCP Server.

Before making any modifications to this codebase, you must read, understand, and strictly adhere to the guidelines, architectural safeguards, and development workflows outlined below.

📋 Table of Contents

Codebase Architecture & File Structure
Dynamic Scoping & Gatekeeping (Least Privilege)
GCP REST & Client API Safeguards (CRITICAL) 3.5. Native Agent Architecture: A2A vs Low-Code (Employee-Made) 3.7. Vertex AI Agent Platform Skills
Step-by-Step Blueprint to Add a New Tool
Operational Protocol for Surgical Code Editing
Testing & Verification Protocol

1. Codebase Architecture & File Structure

This project is a Model Context Protocol (MCP) server written in TypeScript (ESM).

ge-app-mcp/
├── package.json           # Project manifests and build scripts
├── tsconfig.json          # TypeScript compiler configuration (Target: ES2022 / Module: NodeNext)
├── src/
│   ├── index.ts           # MCP Server entrypoint (stdio or HTTP transport, registers and routes tools)
│   ├── config.ts          # Environment variables and dynamic scope parser
│   ├── gcp.ts             # Request-scoped credentials (ADC in stdio, end-user token over HTTP) and REST helpers
│   ├── http.ts            # Stateless Streamable HTTP transport and Google token verification
│   ├── annotations.ts     # MCP tool annotations (readOnlyHint / destructiveHint)
│   ├── domain/            # Pure, unit-tested domain logic (features, models, assistant, licensing, citations)
│   └── tools/             # Segmented tool implementation modules
│       ├── search.ts      # Search and Conversational RAG tools (Data Plane)
│       ├── admin.ts       # Datastore, schema, web crawler, and control tools (Control Plane)
│       └── billing.ts     # Licensing pools and user seat allocation tools (Billing/Licensing Plane)
└── skills/                # Prompt templates conditioning AI Agents using this server

Read the full file on GitHub · 311 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.

13d ago Changed · +23 lines · +700 tokens per session 0a92c2f04606
2mo ago First seen · 288 lines · 4,518 tokens per session scan A 14c40e0d2559

Subscribe to this mod's changes

ge-app-mcp AGENTS.md is an instructions file published in the GitHub repository miticojo/ge-app-mcp (0 stars, last pushed 14d ago), licensed Apache-2.0. It adds 5,218 tokens to every session, about $0.0209 per session on Opus 5.5. 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.

ge-app-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ge-app-mcp AGENTS.mdmiticojo/ge-app-mcp	Instructions file	0	14d ago	Apache-2.0	A	5,218	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

ge-app-mcp: Instructions file for Codex