$ loading_
Connect OpenAI image generation and editing to MCP for create and edit workflows.
This MCP tool is open-source and auditable, with no declared local secrets or extra remote hosts, and no clear high-risk red flags are evident. Caution is still warranted because it executes local code and, based on its stated purpose, will likely transmit user inputs to OpenAI image model services.
The material explicitly states that no keys or environment variables are required, and there is no indication that the tool requests or exposes additional local credentials. However, if it actually calls OpenAI services, authentication may still rely on host-provided credentials, so the implementation should be verified before installation.
Although the metadata says there is no remote host, the description says it exposes OpenAI's gpt-image-2 as an MCP server. Based on that stated purpose, user prompts and images to be edited will likely be sent to OpenAI-related services. The material does not specify exact domains, data flow, or configurable scope, so transparency is limited.
The system checks mark this tool as executes-code, indicating that it runs local server code to provide functions such as generate_image and edit_image. This is a normal execution characteristic for MCP tools, and the current material does not show any request for high-risk system privileges unrelated to image processing.
By its stated functionality, the tool will at minimum handle user-provided images and prompts, likely reading images for editing and returning generated outputs. The available material does not describe its local file read/write scope or whether it persists caches or logs, so its data access should be treated as limited but insufficiently disclosed.
Positive factors are that it is open-source under the MIT License, making the code auditable in principle, which materially lowers overall risk. However, it comes from a third-party registry, has 0 stars, unknown maintenance status, and no README, so supply-chain maturity and verifiability are only moderate; review the source and dependencies first.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "gpt-image-2-mcp" yet — see the docs or source repo.
Use generate_image to create a promo image for minimalist wireless earbuds: white background, soft shadows, modern tech feel, suitable for an ecommerce homepage banner.
A brand-aligned product promo image ready for web or marketing use.
Use edit_image to modify this poster: keep the main subject unchanged, change the background to a sunset beach scene, and enhance the overall warm tones.
An updated poster with the subject preserved, background replaced, and colors refined.
Start an iterative edit session: first transform this illustration into a cyberpunk style, then keep refining lighting, colors, and details each round until it fits a game cover.
A final cover image refined over multiple rounds with clear stylistic progression.
Generate images from prompts and browse or load saved images inline.
Generate, edit, and iteratively refine images from any MCP client
Generate and edit images across providers through one unified MCP API.
Edit, clean up, and generate images with Gemini-powered AI workflows.
Create GPT Image 2 jobs via MCP and track status and pricing.
Generate, edit, and compose images with automatic OpenAI model selection.