Skip to main content
Glama
README.md
# Image3 Prompt MCP

Image3 Prompt MCP is a read-only MCP server for GPT Image 2 prompt research. It lets Codex, Claude Code, Cursor, OpenClaw, and other MCP hosts search the public Image3 prompt gallery, inspect complete prompts, list categories, and turn rough ideas into structured prompt briefs.

- Prompt gallery: https://image3.org/prompts/gpt-image-2
- Prompt Architect docs: https://image3.org/docs/gpt-image-2-prompt-architect
- Generator: https://image3.org/models/gpt-image-2
- OpenClaw skill source: [openclaw/gpt-image-2-prompt-architect/SKILL.md](openclaw/gpt-image-2-prompt-architect/SKILL.md)
- Chinese README: [README.zh-CN.md](README.zh-CN.md)

The server is intentionally read-only. It does not generate images, spend credits, create accounts, or require an API key.

## Tools

| Tool                 | Purpose                                                                  |
| -------------------- | ------------------------------------------------------------------------ |
| `search_prompts`     | Search Image3 prompts by query, category, language, and featured status. |
| `get_prompt`         | Fetch one complete sanitized prompt by slug or id.                       |
| `list_categories`    | List prompt categories and counts.                                       |
| `build_prompt_brief` | Turn a rough idea into a deterministic structured prompt brief.          |

Every prompt result includes its canonical Image3 source page.

## Install from GitHub

```json
{
  "mcpServers": {
    "image3": {
      "command": "npx",
      "args": ["-y", "github:gpt-img-2/image3-prompt-mcp"]
    }
  }
}
```

Codex:

```bash
codex mcp add image3 -- npx -y github:gpt-img-2/image3-prompt-mcp
```

OpenClaw:

```bash
openclaw mcp add image3 \
  --command npx \
  --arg -y \
  --arg github:gpt-img-2/image3-prompt-mcp \
  --include 'search_prompts,get_prompt,list_categories,build_prompt_brief'

openclaw mcp doctor image3 --probe
```

## Optional environment variables

| Variable                  | Default              | Purpose                                     |
| ------------------------- | -------------------- | ------------------------------------------- |
| `IMAGE3_API_BASE_URL`     | `https://image3.org` | Image3 prompt API origin.                   |
| `IMAGE3_APP_BASE_URL`     | `https://image3.org` | Origin used for canonical source links.     |
| `IMAGE3_FETCH_TIMEOUT_MS` | `20000`              | Prompt API timeout from 1,000 to 60,000 ms. |

## Development

```bash
pnpm install
pnpm validate
pnpm smoke:live
```

`pnpm validate` runs type checking, unit tests, a build, and a local MCP handshake/tool-call smoke test. `pnpm smoke:live` additionally verifies the public Image3 prompt API.

TDQS

A4.2/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct role: searching gallery previews, retrieving a full prompt, listing categories, and building a prompt brief. The overlap between search_prompts and get_prompt is well-handled because search returns concise previews while get_prompt requires a returned identifier and returns the complete prompt.

Naming Consistency5/5

All tool names follow the same verb_noun snake_case pattern: search_prompts, get_prompt, list_categories, and build_prompt_brief. The verbs are specific and consistent with each operation.

Tool Count5/5

Four tools is well-scoped for a prompt gallery MCP. Each tool earns its place and there is no unnecessary duplication or excessive surface area.

Completeness5/5

The server covers the core workflow of discovering prompts, retrieving full prompt details, browsing categories, and constructing a new prompt brief. Read-only gallery operations plus the brief-building step form a complete, sensible workflow with no obvious dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo issues