mcp-review

mcp-review is a command for Claude Code from fabriciofs/mcp-postgres. It costs 0 tokens per session (1,053 once invoked), scanned A, original, MIT.

A Portuguese-language code-review command for MCP servers. MCP is a standard way for an AI agent to connect to tools and data sources.

In plain words
What is it for?
Use it to inspect MCP server code for issues such as SQL injection, missing input validation, exposed credentials, unsafe database operations, and incorrect tool registration.
Why use it?
It gives reviews a fixed checklist covering security, server setup, tool design, validation, secrets, and error handling.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Install

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.

agentmods
npx agentmods add commands/fabriciofs/mcp-postgres/mcp-review
Clone the repo
git clone --depth 1 https://github.com/fabriciofs/mcp-postgres

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-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/fabriciofs/mcp-postgres/mcp-review.svg)](https://agentmods.dev/commands/fabriciofs/mcp-postgres/mcp-review)
Your own site
<a href="https://agentmods.dev/commands/fabriciofs/mcp-postgres/mcp-review"><img src="https://agentmods.dev/badge/commands/fabriciofs/mcp-postgres/mcp-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,053 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01053
Opus 5 $0.00000 $0.00526
Sonnet 5 $0.00000 $0.00211
Haiku 4.5 $0.00000 $0.00105

Measured 5d ago against content hash 14e35b29b55a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mcp-review 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/mcp-review.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Code Review

Você é um revisor de código especializado em servidores MCP. Analise o código fornecido seguindo este checklist rigoroso.

Checklist de Review

1. Segurança (CRÍTICO)

  • SQL Injection: Todas as queries usam parâmetros? Nunca concatenação de strings?
  • Input Validation: Todos os inputs são validados com Zod?
  • Secrets: Credenciais estão em variáveis de ambiente? Nada hardcoded?
  • Privilege: Operações destrutivas (DELETE, DROP) estão bloqueadas ou protegidas?
  • Output Sanitization: Dados sensíveis são filtrados antes de retornar?
// RUIM - SQL Injection
const query = `SELECT * FROM users WHERE name = '${name}'`;

// BOM - Parametrizado
request.input("name", sql.VarChar, name);
const query = "SELECT * FROM users WHERE name = @name";

2. Estrutura do MCP

  • McpServer: Configurado com name e version?
  • Transport: Usando StdioServerTransport corretamente?
  • Error Handling: server.connect() tem .catch()?
  • Tool Registration: Tools registradas antes de connect()?

3. Design de Tools

  • Single Responsibility: Cada tool faz uma coisa só?
  • Naming: Nomes são descritivos? (sql_select, file_read, não "query" ou "do")
  • Description: Descrições são claras para o LLM entender quando usar?
  • Schema: Cada parâmetro tem .describe() explicativo?
  • Return Format: Retorna content[] e structuredContent?
// BOM - Schema bem documentado
inputSchema: z.object({
  query: z.string()
    .describe("SQL SELECT query. Use @param for parameters."),
  params: z.record(z.unknown())
    .optional()
    .describe("Named parameters to bind. Keys without @."),
  limit: z.number()
    .int()
    .positive()
    .max(1000)
    .default(100)
    .describe("Max rows to return (default 100, max 1000)."),
})

4. Error Handling

  • Try/Catch: Operações async estão em try/catch?
  • Error Messages: Erros são informativos mas não expõem detalhes internos?
  • isError Flag: Erros retornam { isError: true }?
  • Graceful Degradation: Falhas parciais são tratadas?

Read the full file on GitHub · 129 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. 5d ago First seen · 129 lines · 0 tokens per session scan A 14e35b29b55a

Subscribe to this mod's changes

mcp-review is a command published in the GitHub repository fabriciofs/mcp-postgres (1 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,053 tokens. 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.