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.
curl -O https://raw.githubusercontent.com/Luizcc87/glpi-mcp-v2/main/AGENTS.mdgit clone --depth 1 https://github.com/Luizcc87/glpi-mcp-v2Wrote 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.
[](https://agentmods.dev/instructions/luizcc87/glpi-mcp-v2/agents-md)<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.
<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>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 | $0.02755 | $0.02755 |
| Opus 5.5 | $0.01102 | $0.01102 |
| Sonnet 5 | $0.00551 | $0.00551 |
| Haiku 4.5 | $0.00276 | $0.00276 |
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 5d 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.
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).
- Usada exclusivamente pelas 3 ferramentas de Base de Conhecimento (
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.
- Ferramentas de leitura (
- 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)ouglpi_get_change(id=N). - NUNCA faça chamadas subsequentes para
glpi_get_*_timelinese você já chamouglpi_get_*. A timeline completa (followups, tarefas, soluções) já vem embutida no campotimelinedo retorno.
- Ao analisar um ticket, problema ou mudança, chame
- Filtre Sempre no Servidor MCP:
- Use os parâmetros de paginação (
limit,start) e filtros (filterem RSQL) na chamada MCP. - Não puxe grandes volumes de dados desnecessários para filtrar em memória.
- Use os parâmetros de paginação (
- 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.
- 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
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.
- 5d ago First seen · 149 lines · 2,755 tokens per session scan A 8f4dc8941037
glpi-mcp-v2 AGENTS.md is an instructions file published in the GitHub repository Luizcc87/glpi-mcp-v2 (0 stars, last pushed 6d ago), licensed MIT. It adds 2,755 tokens to every session, about $0.0110 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.
Other instructions, from other repositories
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).
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.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.