Codex Imagem

codex_image_generate

Gera uma imagem a partir de um texto, usando a cota de imagens da assinatura ChatGPT conectada (não consome créditos de API). Retorna um link de download do PNG, que também fica na aba Arquivos do mcp.ai. Leva cerca de 1 minuto. A dimensão é escolhida pelo gerador e não pode ser fixada; descreva enquadramento e proporção dentro do próprio prompt (ex.: 'composição horizontal, bem largo'). Uma imagem por chamada.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "codex_image_generate"
  }
}

Input Schema

Name	Required	Description	Default
`prompt`	Yes
`account`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedAug 21, 2026

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Extends beyond annotations with meaningful details: quota usage, timing, output link, storage in Files tab, and dimension limitation. No contradiction with annotations; annotations are generic while this adds specific behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences, front-loaded with the core action resins. Efficiently packs quota, timing, output, and constraint without fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, so description carries burden to explain result: download link also in Files tab. Covers quota, timing, dimension limitation scare. Missing explanation of 'account' parameter, but overall sufficient for a simple generation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage, so description must compensate. It does explain usage of 'prompt' (include framing and aspect ratio) but does not mention 'account' parameter at all. Partial compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the verb+resource: generates an image from text. Distinct from sibling 'codex_image_subscription' which handles subscription info. Adds specifics (uses ChatGPT image quota, not API credits) that help differentiate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context: consumes image quota, takes ~1 minute, one image per call. Mentions constraints (dimension cannot be fixed, describe framing in prompt). Does not explicitly name alternatives, but the usage scenario is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Codex Imagem tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.