MCP_Compras: Instructions file for Claude Code

CLAUDE.md

MCP_Compras CLAUDE.md is an instructions file for Claude Code from opedrosoares/MCP_Compras. It costs 1,145 tokens per session, scanned A, original, MIT.

A project instruction file for an MCP server that combines public Czech government procurement APIs for analysts. It records coding conventions, tool naming, shared parameter descriptions, and response formats.

In plain words
What is it for?
Use it when adding or changing tools in the procurement MCP server, organizing modules, registering imports, or checking that descriptions stay consistent.
Why use it?
It gives future coding sessions a consistent reference and helps prevent duplicated descriptions, naming drift, and incorrectly registered tools.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is opedrosoares/MCP_Compras's own configuration. It tells Claude Code how to work on MCP_Compras 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 MCP_Compras configures →

Reuse

Borrowing it

Nothing to install: this file belongs to opedrosoares/MCP_Compras. 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/opedrosoares/MCP_Compras/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/opedrosoares/MCP_Compras

Made for: Claude Code.

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 MCP_Compras CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/opedrosoares/mcp_compras/claude-md.svg)](https://agentmods.dev/instructions/opedrosoares/mcp_compras/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/opedrosoares/mcp_compras/claude-md"><img src="https://agentmods.dev/badge/instructions/opedrosoares/mcp_compras/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,145 This file is loaded in full into every session.
When invoked 1,145 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01145 $0.01145
Opus 5 $0.00573 $0.00573
Sonnet 5 $0.00229 $0.00229
Haiku 4.5 $0.00114 $0.00114

Measured 7d ago against content hash 36df5bdef895, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

MCP_Compras CLAUDE.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 7d 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.

CLAUDE.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Notas para sessões futuras

Servidor MCP que reúne as APIs públicas do ecossistema Compras.gov.br (Dados Abertos, PNCP Consulta, Portal da Transparência/CGU e rotas abertas do Comprasnet Contratos) em ~70 tools voltadas a analistas de licitação.

Framework

FastMCP 2.x (não o SDK oficial mcp[cli]). Consistente com o mcp-inpi. O SEI Pro usa mcp[cli] — os dois padrões coexistem no portfólio.

Padrão SSoT para descriptions

Toda description de parâmetro vive em src/compras_mcp/schemas.py (Pydantic Field(description=...)). As tools nunca duplicam — leem via from compras_mcp.tools._helpers import desc; desc(Modelo, "campo"). Drift é detectado pelo teste em tests/test_server.py::test_ssot_*.

Convenções de naming

  • Tools: compras_<dominio>_<verbo>_<recurso> (ex.: compras_arp_saldo_item).
  • Módulos de tool: por domínio em src/compras_mcp/tools/<dominio>.py. Não expor a tool diretamente — registrar com @mcp.tool lendo a instância de compras_mcp.mcp_instance.
  • Para registrar um novo módulo: adicionar from compras_mcp.tools import <modulo> na lista de imports em server.py (a ordem define a ordem de listagem).

Envelope padrão das respostas

Tools listar_* devolvem:

{
  "resultado": [...],
  "_pagina_atual": int,
  "_total_paginas": int,
  "_total_registros": int,
  "_proxima_pagina": int | None,
  "_cache_hit": bool,
  "_latency_ms": float,
}

Tools consultar_* (singular) devolvem {"encontrado": bool, "codigo_consultado": ..., "<recurso>": dict | None, "_cache_hit": ...}. Sempre passar pelo with_latency(payload, started) antes do return.

Clientes HTTP

  • BaseAsyncClient em src/compras_mcp/clients/base.py: retry exponencial para timeout/5xx/429, logging structlog, format_date(value, flavor) para os 3 formatos de data: dados_abertos (YYYY-MM-DD), pncp (yyyyMMdd) e comprasnet (YYYY-MM-DD HH:mm:ss).
  • Subclasses específicas por API. Factories em tools/_helpers.py: make_dados_abertos(s), make_pncp(s), make_transparencia(s), make_comprasnet(s).

Read the full file on GitHub · 91 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. 7d ago First seen · 91 lines · 1,145 tokens per session scan A 36df5bdef895

Subscribe to this mod's changes

MCP_Compras CLAUDE.md is an instructions file published in the GitHub repository opedrosoares/MCP_Compras (2 stars, last pushed 6d ago), licensed MIT. It adds 1,145 tokens to every session, about $0.0057 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens