About this integration
AI image generation and editing MCP server. Gemini + OpenAI, iterative editing, undo/redo.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 1.6.1
- Package
- imgx-mcp
- Last compatibility test
- Not independently tested
Connect your agent
imgx-mcpDocumented from publisher files only; not executed. Provider billing, model availability, and content policies remain external prerequisites.
Capabilities: generate images, edit images, iterative edit history, undo and redo edits, manage output directories and sessions
Connected profiles
Additional details
io.github.somacoffeekyoto/imgx
Source ↗ · Checked 2026-09-171.6.1
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17npm
Source ↗ · Checked 2026-09-17imgx-mcp
Source ↗ · Checked 2026-09-191.6.1
Source ↗ · Checked 2026-09-19Once a provider key is configured, generation, editing, history, undo, redo, and session operations are exposed as direct MCP tool calls.
Source ↗ · Checked 2026-09-19At least one Gemini or OpenAI API key is required and may be supplied through environment variables or the local imgx configuration.
Source ↗ · Checked 2026-09-19The package declares a separate imgx-mcp executable, and the publisher documents launching it with npx in MCP client configuration.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19