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.
git clone --depth 1 https://github.com/opedrosoares/MCP_ComprasWrote 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/mcp/opedrosoares/mcp_compras/mcp-compras)<a href="https://agentmods.dev/mcp/opedrosoares/mcp_compras/mcp-compras"><img src="https://agentmods.dev/badge/mcp/opedrosoares/mcp_compras/mcp-compras/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/mcp/opedrosoares/mcp_compras/mcp-compras"><img src="https://agentmods.dev/badge/mcp/opedrosoares/mcp_compras/mcp-compras.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-compras 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 1mo 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.
What it actually says
{
"mcp-compras": {
"command": "uvx",
"args": [
"compras-mcp"
],
"env": {
"TRANSPARENCIA_API_KEY": "",
"REDIS_URL": "",
"INCLUIR_CPF_COMPLETO": "false"
}
}
}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.
- 1mo ago First seen · 13 lines scan A 7df3f7eafd69
mcp-compras is an MCP server published in the GitHub repository opedrosoares/MCP_Compras (7 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-09-04.
Other mcp servers, from other repositories
mcp-fiscal-brasil
MCP fiscal brasileiro - 44 ferramentas, zero API key. CNPJ, NF-e, Reforma Tributaria IBS/CBS, ICMS, Simples Nacional, NCM/CFOP, indexadores BCB. Runs locally from the mcp-fiscal-brasil Python package.
contaazul-mcp
Conta Azul ERP MCP — sales, customers, finance and NF-e via OAuth 2.0. Read + write, 35 tools. Remote server at api.mcp.ai.
kalshi-mcp-server
Model Context Protocol server for Kalshi prediction markets — native RSA-PSS auth, token-bucket rate limiting, demo/prod safety controls. Runs locally from the kalshi-mcp-server Python package. Needs 6 environment variables to run.
jquants-mcp
MCP server for retrieving Japanese stock market data via J-Quants API v2. Runs locally from the jquants-mcp Python package. Needs 1 environment variable to run.
mcp-dados-br
Servidor MCP com dados públicos brasileiros: IBGE, Banco Central, INMET, Câmara dos Deputados e Senado Federal. Runs locally from the mcp-dados-br Python package. Needs 2 environment variables to run.
kalshi
MCP server for Kalshi prediction markets - search, analyze, and trade prediction markets through Claude Desktop. Runs locally from the kalshi-mcp Python package. Needs 2 environment variables to run.