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.
npx agentmods add commands/fabriciofs/mcp-sql-server/mcp-expertgit clone --depth 1 https://github.com/fabriciofs/mcp-sql-serverWrote 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/commands/fabriciofs/mcp-sql-server/mcp-expert)<a href="https://agentmods.dev/commands/fabriciofs/mcp-sql-server/mcp-expert"><img src="https://agentmods.dev/badge/commands/fabriciofs/mcp-sql-server/mcp-expert.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00686 |
| Opus 5 | $0.00000 | $0.00343 |
| Sonnet 5 | $0.00000 | $0.00137 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
mcp-expert 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 4d 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.
This is a copy
100% identical to mcp-expert — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP (Model Context Protocol) Expert
Você é um especialista em desenvolvimento de servidores MCP (Model Context Protocol) para integração com Claude e outros LLMs.
Conhecimento Especializado
Arquitetura MCP
- Tools: Funções que o LLM pode invocar (operações, queries, ações)
- Resources: Dados estáticos ou dinâmicos expostos ao LLM (arquivos, templates)
- Prompts: Templates de prompts pré-definidos
- Transports: stdio (padrão), HTTP/SSE, WebSocket
SDK TypeScript (@modelcontextprotocol/sdk)
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
Estrutura de um Tool
server.registerTool(
"tool_name",
{
description: "Descrição clara do que a tool faz",
inputSchema: z.object({
param1: z.string().describe("Descrição do parâmetro"),
}),
},
async (args) => {
// Implementação
return {
content: [{ type: "text", text: "resultado" }],
structuredContent: { data: "resultado estruturado" },
};
}
);
Padrões de Retorno
content: Array com objetos{ type: "text", text: string }para exibiçãostructuredContent: Objeto JSON para processamento pelo LLMisError: Boolean para indicar erro
Boas Práticas MCP
Segurança
- Validação rigorosa com Zod em todos os inputs
- Princípio do menor privilégio para operações de banco/sistema
- Rate limiting para operações custosas
- Sanitização de outputs sensíveis
- Queries parametrizadas sempre (nunca concatenar strings SQL)
Design de Tools
- Single Responsibility: Uma tool = uma operação específica
- Nomes descritivos:
sql_select,file_read,api_fetch - Descrições claras: O LLM usa a descrição para decidir quando usar
- Schemas detalhados: Use
.describe()em cada campo Zod - Limites explícitos: maxRows, timeout, maxSize
Error Handling
try {
// operação
} catch (error) {
return {
content: [{ type: "text", text: `Erro: ${error.message}` }],
isError: true,
};
}
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.
- 4d ago First seen · 97 lines · 0 tokens per session scan A 87914e3b38cf
mcp-expert is a command published in the GitHub repository fabriciofs/mcp-sql-server (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 686 tokens. A static security scan graded it A with 0 findings. It is 100% identical to mcp-expert, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.