OpenAI GPT ImageSAFE
A Model Context Protocol (MCP) tool server for OpenAI's GPT-4o/gpt-image-1 image generation and editing APIs.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) tool server for OpenAI's GPT-4o/gpt-image-1 image generation and editing APIs.
- Generate images from text prompts using OpenAI's latest models.
- Edit images (inpainting, outpainting, compositing) with advanced prompt control.
- Supports: Claude Desktop, Cursor, VSCode, Windsurf, and any MCP-compatible client.
✨ Features
- create-image: Generate images from a prompt, with advanced options (size, quality, background, etc).
- edit-image: Edit or extend images using a prompt and optional mask, supporting both file paths and base64 input.
- File output: Save generated images directly to disk, or receive as base64.
🚀 Installation
git clone https://github.com/SureScaleAI/openai-gpt-image-mcp.git cd openai-gpt-image-mcp yarn install yarn build
🔑 Configuration
Add to Claude Desktop or VSCode (including Cursor/Windsurf) config:
{
"mcpServers": {
"openai-gpt-image-mcp": {
259115bef675OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add openai-gpt-image-mcp --env AZURE_OPENAI_API_KEY=${AZURE_OPENAI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"openai-gpt-image-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"AZURE_OPENAI_API_KEY": "${AZURE_OPENAI_API_KEY}"
}
}
}
}Exposed tools (2)
0 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
create-image | write | |
edit-image | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
.cursorignore
@modelcontextprotocol/sdk, openai, @types/node, typescript
test_cat_image.png
test_cat_image_edited.png
test_cat_with_moustache.png
Gates applied: no_behavioural_pass.
259115bef675full audit observations/trust-audit/mcp-server/surescaleai__openai-gpt-image.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 259115bef675 | SAFE | B | 89 | first audit |
Questions
What is the OpenAI GPT Image MCP server?
A Model Context Protocol (MCP) tool server for OpenAI's GPT-4o/gpt-image-1 image generation and editing APIs.
What tools does OpenAI GPT Image expose?
2 in total: 0 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is OpenAI GPT Image safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does OpenAI GPT Image need?
It reads AZURE_OPENAI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does OpenAI GPT Image run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as openai-gpt-image-mcp at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (259115bef675), read on 2026-10-07. The repository is watched and re-audited when it changes.