mcp-create-tool

mcp-create-tool is a command for Claude Code from fabriciofs/mcp-sql-server. It costs 0 tokens per session (1,183 once invoked), scanned A, a copy of mcp-create-tool, MIT.

A coding assistant for creating tools that MCP servers can expose to AI agents. It provides a TypeScript example for defining inputs, descriptions, defaults, choices, and the code that handles a request.

In plain words
What is it for?
Use it when adding a tool to an MCP server, especially when you need input validation, documented parameters, and a handler for the operation.
Why use it?
It helps structure new MCP tools so their inputs and expected behavior are clearly defined.

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-sql-server/mcp-create-tool
Clone the repo
git clone --depth 1 https://github.com/fabriciofs/mcp-sql-server

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 1,183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.01183
Opus 5 $0.00000 $0.00592
Sonnet 5 $0.00000 $0.00237
Haiku 4.5 $0.00000 $0.00118

Measured 2d ago against content hash 59325ab2b5f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-create-tool 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 2d 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

This is a copy

100% identical to mcp-create-tool — 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.

.claude/commands/mcp-create-tool.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tool Creator

Você é um assistente especializado em criar novas tools para servidores MCP.

Template de Tool

import { z } from "zod";

// 1. Definir schema de input com descrições detalhadas
const toolInputSchema = z.object({
  requiredParam: z.string()
    .min(1)
    .describe("Descrição clara do parâmetro obrigatório"),

  optionalParam: z.string()
    .optional()
    .describe("Descrição do parâmetro opcional"),

  paramWithDefault: z.number()
    .int()
    .positive()
    .max(1000)
    .default(100)
    .describe("Parâmetro com valor padrão (default: 100, max: 1000)"),

  enumParam: z.enum(["option1", "option2", "option3"])
    .default("option1")
    .describe("Escolha entre: option1, option2, option3"),
});

// 2. Registrar a tool
server.registerTool(
  "tool_name", // snake_case, descritivo
  {
    description: `Descrição completa da tool.

Quando usar:
- Caso de uso 1
- Caso de uso 2

Limitações:
- Limitação 1
- Limitação 2

Exemplos:
- Exemplo de input 1
- Exemplo de input 2`,
    inputSchema: toolInputSchema,
  },
  async (args) => {
    // 3. Implementar handler
    try {
      // Lógica da tool
      const result = await executeOperation(args);

      // 4. Retornar resultado formatado
      return {
        content: [
          {
            type: "text",
            text: JSON.stringify(result, null, 2),
          },
        ],
        structuredContent: result,
      };
    } catch (error) {
      // 5. Tratamento de erro
      return {
        content: [
          {
            type: "text",
            text: `Error: ${error instanceof Error ? error.message : "Unknown error"}`,
          },
        ],
        isError: true,
      };
    }
  }
);

Checklist de Criação

Naming

  • Nome em snake_case
  • Prefixo indica domínio (sql_, file_, api_, etc.)
  • Nome descreve a ação (select, list, create, delete)

Schema (Zod)

  • Todos os parâmetros têm .describe()
  • Validações apropriadas (min, max, regex, etc.)
  • Defaults para parâmetros opcionais sensatos
  • Tipos corretos (string, number, boolean, enum)

Read the full file on GitHub · 198 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. 2d ago First seen · 198 lines · 0 tokens per session scan A 59325ab2b5f7

Subscribe to this mod's changes

mcp-create-tool 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 1,183 tokens. A static security scan graded it A with 0 findings. It is 100% identical to mcp-create-tool, differing in 0 lines, and is treated as a copy.