OpenAI Image runs on your own machine — the client starts it, so there is no endpoint to ping. 346 installs a week from npm. Last commit 13 Sep 2026.
OpenAI image generation MCP server for Model Context Protocol hosts
We read the source, 19 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
fs.writeFileSync(outFd, pdfBuffer);
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const fullPath = path.join(stagingDir, filename);
const child = spawn(process.execPath, [script], {
if (isUnder(resolvedAbs, sshDir)) return { hit: true, reason: '~/.ssh/** is sensitive' };
<script src="https://appsforoffice.microsoft.com/lib/1.1/hosted/office.js"></script>
const entries = fs.readdirSync(workspacePath, { withFileTypes: true });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-server-openai-image -- npx -y @mindstone/mcp-server-openai-image
{
"mcpServers": {
"mcp-server-openai-image": {
"args": [
"-y",
"@mindstone/mcp-server-openai-image"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-server-openai-image]
command = "npx"
args = ["-y", "@mindstone/mcp-server-openai-image"]
{
"mcpServers": {
"mcp-server-openai-image": {
"args": [
"-y",
"@mindstone/mcp-server-openai-image"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-server-openai-image": {
"args": [
"-y",
"@mindstone/mcp-server-openai-image"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
OPENAI_API_KEY (OpenAI API key with image generation access), MCP_WORKSPACE_PATH (Workspace directory for saving generated images), OPENAI_IMAGE_MODEL (Override the default OpenAI image model identifier), OPENAI_IMAGE_REQUEST_TIMEOUT_MS (Outbound HTTP request timeout in milliseconds (max 1800000)), MCP_ALLOWED_SYMLINK_ROOTS (JSON array of absolute paths the connector may read through (and write generated images through) in-workspace symlinks that resolve into them. Mirrors the host's built-in file-tool declared-Space roots. Malformed or partially-malformed values fail closed to workspace-only. Optional; standalone users omit it.), MCP_HTTP_PORT (When set, serve MCP over HTTP on this port bound to 127.0.0.1 (loopback only) instead of stdio. Intended for host-managed local deployments; stdio hosts omit it.).
The author declared them in the registry entry; get the values from the project itself.
Gamma AI presentation generation MCP server for Model Context Protocol hosts
Kling AI video generation MCP server for Model Context Protocol hosts
Napkin AI visual generation MCP server for Model Context Protocol hosts
Zendesk MCP server for Model Context Protocol hosts
ServiceNow ITSM MCP server for Model Context Protocol hosts
GitLab MCP (Model Context Protocol) server for AI agents
PandaDoc document automation MCP server for Model Context Protocol hosts
Trello Model Context Protocol (MCP) Server for AI Agents
Answers built from our own checks of this server.