Mcp Openai

io.github.AceDataCloudv2026.10.4.1Updated Oct 4, 2026

MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud

VerifiedStreamable HTTPWeb executableAI & MLMedia & Design

Overview

AI-generated overview

Lets an assistant call OpenAI models through AceDataCloud for chat, image generation and editing, embeddings, and audio.

What it does
Exposes OpenAI capabilities as MCP tools: chat completions, the Responses API, image generation and editing, text embeddings, text-to-speech, and audio transcription. It also lists available chat, image, and embedding models and returns a usage guide. Requests are routed through the AceDataCloud platform rather than a direct OpenAI account.
When to use it
Use it when an assistant should generate text, images, or embeddings, or transcribe and synthesize audio, without integrating the OpenAI SDK directly. It suits clients that can reach a hosted MCP endpoint or run a local Python process.
Requirements
An AceDataCloud API token supplied in the ACEDATACLOUD_API_TOKEN environment variable, plus network access to the AceDataCloud API. It can run as a hosted remote endpoint or locally via the mcp-openai-pro PyPI package with uvx or pip. Optional settings include ACEDATACLOUD_API_BASE_URL, OPENAI_REQUEST_TIMEOUT, MCP_SERVER_NAME, and LOG_LEVEL.
Before you install
The token is a billable credential for the AceDataCloud platform, so usage may incur charges. Prompts, images, and audio are sent to AceDataCloud and onward to OpenAI, so avoid confidential content. The package name matters: the unrelated mcp-openai package on PyPI is not maintained by AceDataCloud, so existing uvx configurations should point at mcp-openai-pro.

Installation

In SourceWeft

  1. Open Mcp Openai in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "mcp-openai": {
      "type": "http",
      "url": "https://openai.mcp.acedata.cloud/mcp"
    }
  }
}

README

OpenAIMCP

A Model Context Protocol (MCP) server for OpenAI API access using AceDataCloud.

Interact with OpenAI models for chat completions, image generation, text embeddings, and more — directly from Claude, VS Code, or any MCP-compatible client.

The AceDataCloud distribution is mcp-openai-pro. The unrelated mcp-openai package on PyPI is not maintained by AceDataCloud. Update existing uvx configurations to the new package name; the hosted MCP URL is unchanged.

Features

  • Chat Completions — Access GPT-4, GPT-4o, GPT-5, o1, o3, o4-mini, and many more models
  • Responses API — Extended model variant support including dated releases and search-preview models
  • Image Generation — Create images with gpt-image-1, gpt-image-2, GPT Image 2.5 Flare/Sunburst standard or official variants, dall-e-3, and nano-banana models
  • Image Editing — Modify existing images with AI
  • Text Embeddings — Generate vector representations with text-embedding-3 models
  • Audio — Convert text to speech and transcribe audio with whisper-1 or gpt-transcribe

Quick Start

Prerequisites

Get an API token from AceDataCloud.

Installation

bash
pip install mcp-openai-pro

Configuration

Set your API token:

bash
export ACEDATACLOUD_API_TOKEN=your_api_token_here

Run

bash
mcp-openai-pro

Available Tools

ToolDescription
openai_chat_completionCreate chat completions using OpenAI models
openai_create_responseCreate responses using the Responses API
openai_generate_imageGenerate images from text descriptions
openai_edit_imageEdit existing images with AI
openai_create_embeddingCreate text embedding vectors
openai_text_to_speechConvert text to spoken audio
openai_transcribe_audioTranscribe audio from a URL
openai_list_chat_modelsList available chat/completion models
openai_list_image_modelsList available image models
openai_list_embedding_modelsList available embedding models
openai_get_usage_guideGet comprehensive usage guide

Supported Models

Chat Completion Models

  • GPT-5 Series: gpt-5.5, gpt-5.5-pro, gpt-5.4, gpt-5.4-pro, gpt-5.2, gpt-5.1, gpt-5, gpt-5-mini, gpt-5-nano
  • GPT-4 Series: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-4o, gpt-4o-mini, gpt-4
  • Reasoning: o4-mini, o3, o3-mini, o3-pro, o1, o1-mini, o1-pro

Image Models

  • gpt-image-1, gpt-image-1.5, gpt-image-2, gpt-image-2:official, gpt-image-2.5-flare, gpt-image-2.5-flare:official, gpt-image-2.5-sunburst, gpt-image-2.5-sunburst:official, dall-e-3, dall-e-2, nano-banana, nano-banana-2, nano-banana-pro
  • GPT Image :official variants settle from actual text-input, image-input, and image-output tokens.

Embedding Models

  • text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002

Audio Transcription Models

  • whisper-1, gpt-transcribe

Usage Examples

Chat Completion

openai_chat_completion(    messages=[{"role": "user", "content": "Explain quantum computing in simple terms"}],    model="gpt-4.1")

Image Generation

openai_generate_image(    prompt="A serene Japanese garden with cherry blossoms at sunset, photorealistic",    model="gpt-image-1",    size="1024x1024")

Text Embeddings

openai_create_embedding(    input="The quick brown fox jumps over the lazy dog",    model="text-embedding-3-small")

Configuration

VariableDescriptionDefault
ACEDATACLOUD_API_TOKENAPI token (required)—
ACEDATACLOUD_API_BASE_URLAPI base URLhttps://api.acedata.cloud
OPENAI_REQUEST_TIMEOUTRequest timeout in seconds60
MCP_SERVER_NAMEMCP server nameopenai
LOG_LEVELLogging levelINFO

Development

bash
# Install dependenciespip install -e ".[dev,test]"
# Run testspytest
# Run linterruff check .

API Reference

Documentation

Documentation

License

MIT

Source: README.md at commit f1012fc

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v2026.10.4.1LatestOct 4, 2026