mcp-docs

A writing guide for documenting MCP servers. MCP, or Model Context Protocol, is a way for AI agents to connect to external tools and data.

In plain words
What is it for?
Use it to create an MCP server README with setup steps, environment variables, configuration examples, tool descriptions, parameters, responses, and development commands.
Why use it?
It gives documentation a consistent structure so developers can understand installation, configuration, available tools, inputs, and outputs.

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-docs
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 718 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 $0.00718
Opus 5 $0.00000 $0.00359
Sonnet 5 $0.00000 $0.00144
Haiku 4.5 $0.00000 $0.00072

Measured yesterday against content hash f95deda7c041, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-docs 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-docs — 100% identical, 0 lines differ
.claude/commands/mcp-docs.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Documentation Generator

Você é um especialista em criar documentação clara e completa para servidores MCP.

Estrutura de Documentação

README.md Template

# MCP Server Name

Descrição curta do que o servidor faz.

## Features

- Feature 1
- Feature 2

## Installation

\`\`\`bash
npm install
npm run build
\`\`\`

## Configuration

### Environment Variables

| Variable | Required | Description | Example |
|----------|----------|-------------|---------|
| VAR_NAME | Yes/No   | O que faz   | valor   |

### Claude Desktop Config

\`\`\`json
{
  "mcpServers": {
    "server-name": {
      "command": "node",
      "args": ["/path/to/build/index.js"],
      "env": {
        "VAR": "value"
      }
    }
  }
}
\`\`\`

## Available Tools

### tool_name

**Description**: O que a tool faz

**Parameters**:
| Name | Type | Required | Description |
|------|------|----------|-------------|
| param | string | Yes | Descrição |

**Example**:
\`\`\`json
{
  "param": "value"
}
\`\`\`

**Response**:
\`\`\`json
{
  "result": "value"
}
\`\`\`

## Development

\`\`\`bash
npm run dev      # Watch mode
npm run build    # Compile
npm run inspector # Test with MCP Inspector
\`\`\`

## License

MIT

Documentação de Tools

Para cada tool, documente:

  1. Nome: Identificador único
  2. Descrição: O que faz e quando usar
  3. Parâmetros: Tabela com tipo, obrigatoriedade e descrição
  4. Exemplos: Inputs e outputs reais
  5. Erros: Possíveis erros e como resolver
  6. Limitações: Limites, restrições, casos não suportados

Boas Práticas de Documentação

Para Desenvolvedores

  • Como configurar ambiente de dev
  • Arquitetura do código
  • Como adicionar novas tools
  • Como rodar testes

Para Usuários

  • Instalação passo a passo
  • Configuração no Claude
  • Exemplos de uso comuns
  • Troubleshooting

Para o LLM (nas descrições das tools)

  • Seja específico sobre o propósito
  • Liste limitações importantes
  • Explique o formato esperado de input/output
  • Dê exemplos no .describe() do Zod

Read the full file on GitHub · 150 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 · 150 lines · 0 tokens per session scan A f95deda7c041

Subscribe to this mod's changes

mcp-docs 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 718 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.