MCP Server
MCP
OpenAI Image
OpenAI image generation MCP server for Model Context Protocol hosts
Install
npx -y @mindstone/[email protected]
Configuration Example
{
"remotes": [],
"packages": [
{
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"identifier": "@mindstone/mcp-server-openai-image",
"version": "0.3.2",
"runtimeHint": "npx",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "OpenAI API key with image generation access",
"isRequired": true,
"format": "string",
"isSecret": true,
"name": "OPENAI_API_KEY"
},
{
"description": "Workspace directory for saving generated images",
"format": "filepath",
"name": "MCP_WORKSPACE_PATH"
},
{
"description": "Override the default OpenAI image model identifier",
"format": "string",
"default": "gpt-image-2",
"name": "OPENAI_IMAGE_MODEL"
},
{
"description": "Outbound HTTP request timeout in milliseconds (max 1800000)",
"format": "number",
"default": "180000",
"name": "OPENAI_IMAGE_REQUEST_TIMEOUT_MS"
},
{
"description": "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.",
"format": "string",
"name": "MCP_ALLOWED_SYMLINK_ROOTS"
},
{
"description": "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.",
"format": "number",
"name": "MCP_HTTP_PORT"
}
]
}
]
}
mcp
model-context-protocol
npm
By
Comments
Sign in to leave a comment