mcp-debug

A troubleshooting reference for Model Context Protocol servers. MCP is a standard that lets an AI application connect to external tools and data sources.

In plain words
What is it for?
Use it to inspect server paths, environment variables, tool registration, schemas, and logs, and to test a server with the MCP Inspector.
Why use it?
It helps diagnose servers that fail to start, connect, register tools, or expose tools correctly.

Command for Claude Code

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-debug
Clone the repo
git clone --depth 1 https://github.com/fabriciofs/mcp-postgres

Made for: Claude Code.

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 901 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 $0.00000 $0.00901
Opus 5 $0.00000 $0.00451
Sonnet 5 $0.00000 $0.00180
Haiku 4.5 $0.00000 $0.00090

Measured yesterday against content hash a669ed277924, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-debug 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 yesterday.

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:

  • mcp-debug — 100% identical, 0 lines differ
.claude/commands/mcp-debug.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Debug Expert

Você é um especialista em debugging e troubleshooting de servidores MCP.

Ferramentas de Debug

MCP Inspector

# Testar servidor MCP interativamente
npx @modelcontextprotocol/inspector

# Ou instalar globalmente
npm install -g @modelcontextprotocol/inspector
mcp-inspector

Logs do Servidor

// Adicionar logging detalhado
console.error("[MCP] Tool chamada:", toolName, args);
console.error("[MCP] Resultado:", JSON.stringify(result, null, 2));

IMPORTANTE: Use console.error para logs em servidores stdio, pois console.log interfere no protocolo.

Problemas Comuns e Soluções

1. Servidor não inicia

Sintomas: Claude não consegue conectar ao MCP

Verificar:

  • Path do executável está correto no config?
  • node build/index.js roda sem erros?
  • Variáveis de ambiente estão definidas?
# Testar manualmente
SQL_SERVER=localhost SQL_DATABASE=mydb node build/index.js

2. Tool não aparece no Claude

Sintomas: Tool registrada mas não disponível

Verificar:

  • Tool foi registrada ANTES de server.connect()?
  • Nome da tool é único?
  • Schema Zod é válido?
// Debug: listar tools registradas
console.error("[MCP] Tools:", server.getRegisteredTools?.());

3. Erro de parsing JSON

Sintomas: SyntaxError: Unexpected token

Causas comuns:

  • console.log() em servidor stdio (usar console.error)
  • Output não-JSON misturado no stdout
  • Encoding incorreto

4. Timeout de conexão

Sintomas: Tool demora e falha

Soluções:

// Adicionar timeout explícito
const controller = new AbortController();
const timeout = setTimeout(() => controller.abort(), 30000);

try {
  const result = await operacao({ signal: controller.signal });
} finally {
  clearTimeout(timeout);
}

5. Erro de validação Zod

Sintomas: ZodError: Invalid input

Debug:

const schema = z.object({...});

// Testar schema manualmente
const result = schema.safeParse(input);
if (!result.success) {
  console.error("[MCP] Validation errors:", result.error.issues);
}

Read the full file on GitHub · 151 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. yesterday First seen · 151 lines · 0 tokens per session scan A a669ed277924

Subscribe to this mod's changes

mcp-debug is a command published in the GitHub repository fabriciofs/mcp-postgres (1 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 901 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.