What is glpi-mcp-v2 AGENTS.md?

A project instruction file for a GLPI server integration. GLPI is an IT service-management system for handling things such as support tickets, assets, users, and knowledge-base articles.

It guides agents using the GLPI server's ticket, asset, administration, statistics, and knowledge-base functions through its APIs.

It gives an agent rules for choosing the integration's tools and for respecting security limits when working with GLPI.

How Luizcc87/glpi-mcp-v2 configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Luizcc87/glpi-mcp-v2. 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/Luizcc87/glpi-mcp-v2/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Luizcc87/glpi-mcp-v2

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/luizcc87/glpi-mcp-v2/agents-md/github.svg)](https://agentmods.dev/instructions/luizcc87/glpi-mcp-v2/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/luizcc87/glpi-mcp-v2/agents-md"><img src="https://agentmods.dev/badge/instructions/luizcc87/glpi-mcp-v2/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/luizcc87/glpi-mcp-v2/agents-md"><img src="https://agentmods.dev/badge/instructions/luizcc87/glpi-mcp-v2/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,770 This file is loaded in full into every session.

When invoked 2,770 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	$0.02770	$0.02770
Opus 5.5	$0.01108	$0.01108
Sonnet 5.5	$0.00554	$0.00554
Haiku 4.5	$0.00277	$0.00277

Measured 14d ago against content hash 16bcd0c04b8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

glpi-mcp-v2 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 14d 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 · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Instruções para Agentes de IA (GLPI MCP Server)

Este documento instrui agentes de IA (como Claude Code, Hermes Agent, Antigravity, OpenClaw e Codex) sobre como interagir com o glpi-mcp-v2, executar tarefas de ITSM, selecionar as ferramentas adequadas e respeitar os limites de segurança.

1. Visão Geral e Arquitetura

O glpi-mcp-v2 é um servidor Model Context Protocol que funciona como um gateway unificado entre agentes de IA e a plataforma GLPI (versões 10 e 11), expondo 31 ferramentas padronizadas com o prefixo glpi_.

Arquitetura Híbrida (v2 + v1)

API v2 (High-Level REST API via OAuth2):
- Usada por 28 ferramentas: Tickets, Problems, Changes, Assets (Computers), Administração (Users/Groups/Plugins) e Estatísticas.
- Vantagens: traz dados completos com timeline embutida em 1 requisição, suporta filtros RSQL e autenticação JWT Bearer sem gerenciamento de sessão PHP em memória.
API v1 (API REST Legada via App-Token & User-Token):
- Usada exclusivamente pelas 3 ferramentas de Base de Conhecimento (glpi_search_knowbase, glpi_get_knowbase_item, glpi_search_faq).
- Motivo: compatibilidade com instâncias do GLPI onde a API v2 ainda não implementa controllers de Base de Conhecimento (retornando 404 em /Knowledgebase/Article).

2. Regras de Ouro e Gates de Segurança

Ações Destrutivas e Mudanças de Estado:
- Ferramentas de leitura (glpi_search_*, glpi_get_*) podem ser executadas autonomamente para obter contexto e responder a dúvidas.
- Ferramentas de escrita (glpi_create_*, glpi_update_*, glpi_add_*_followup) alteram dados reais de produção. O agente deve montar a proposta, exibir os dados pretendidos e aguardar aprovação humana explícita antes de disparar a ação.
Eficiência de Contexto (Regra de 1 Chamada):
- Ao analisar um ticket, problema ou mudança, chame glpi_get_ticket(id=N), glpi_get_problem(id=N) ou glpi_get_change(id=N).
- NUNCA faça chamadas subsequentes para glpi_get_*_timeline se você já chamou glpi_get_*. A timeline completa (followups, tarefas, soluções) já vem embutida no campo timeline do retorno.
Filtre Sempre no Servidor MCP:
- Use os parâmetros de paginação (limit, start) e filtros (filter em RSQL) na chamada MCP.
- Não puxe grandes volumes de dados desnecessários para filtrar em memória.
Respostas com Grandes Volumes:
- Se uma consulta trouxer dados que excedam a janela de contexto e forem salvos em disco pelo harness, não crie scripts Python ou pipelines ad-hoc de jq. Delegue a exploração e sumarização para um subagente de pesquisa/exploração.

Read the full file on GitHub · 149 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.

14d ago Changed · +15 tokens per session 16bcd0c04b8c
1mo ago First seen · 149 lines · 2,755 tokens per session scan A 8f4dc8941037

Subscribe to this mod's changes

glpi-mcp-v2 AGENTS.md is an instructions file published in the GitHub repository Luizcc87/glpi-mcp-v2 (0 stars, last pushed 14d ago), licensed MIT. It adds 2,770 tokens to every session, about $0.0111 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 2026-09-22.

Building agents Project management

glpi-mcp-v2 AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
glpi-mcp-v2 AGENTS.mdLuizcc87/glpi-mcp-v2	Instructions file	0	14d ago	MIT	A	2,770	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	279k	yesterday	MIT	A	4,325	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

glpi-mcp-v2: Instructions file for Codex