OpenAI Connector for AI agents.
10 live capabilities
Automate content generation and model fine-tuning.
Waiting for input…
Why people use OpenAI
OpenAI for Automated Content Generation and Safety
This Connector lets your agent do it all in one go. You tell your agent to create a safe social media post with a matching image, and it handles the chat, the moderation, and the image generation in one sequence. You get a finished product instead of a list of tasks to do manually.
What Vinkius changes
Your agent gets a direct line to OpenAI's full feature set without you writing extra glue code.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Automated Social Media Production
A marketing agent needs to generate a blog post and then create a matching header image using generate_image.
- Real-world use case 02
Real-time Content Safety
A customer support bot needs to check if a user's message is toxic before responding using moderate_content.
- Real-world use case 03
Structured Data Extraction
A data analyst wants an agent to extract product details from a messy list and save it as JSON via structured_output.
Complete set · 10capabilities
The complete OpenAI capability set.
These are the exact actions your AI can choose when you ask it to work with OpenAI.
01—04
4 capabilities in this set.
Part of 10 available through OpenAI.
- 01 Capability
Structured output
Get a JSON response from a prompt. It ensures the AI follows a specific format for your downstream apps.
- 02 Capability
List models
See every model currently available in the OpenAI ecosystem. Use this to check which models your agent can access.
- 03 Capability
Create embedding
Convert your text into vector representations. This is perfect for setting up semantic search or RAG systems.
- 04 Capability
Create fine tune
Start a new fine-tuning job using a specific training file ID. It handles the request to train your custom model.
05—07
3 capabilities in this set.
Part of 10 available through OpenAI.
- 05 Capability
Chat completion
Get a response from models like gpt-4o or gpt-4o-mini. You just provide the messages and the model you want to use.
- 06 Capability
List fine tunes
See all your current and past fine-tuning jobs. This helps you track the status of your custom model training.
- 07 Capability
Generate image
Create a new image using DALL-E 3. Your agent sends a prompt and gets back a URL for the result.
08—10
3 capabilities in this set.
Part of 10 available through OpenAI.
- 08 Capability
List files
See the files you've uploaded to OpenAI. This is useful for managing training data or assistant files.
- 09 Capability
Moderate content
Check if a piece of text violates safety policies. It returns a score and category for every violation.
- 10 Capability
List assistants
Browse through your configured OpenAI Assistants. Use this to see what assistants are ready for your agent to use.
Set up in minutes
One URL. Then ask OpenAI to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use OpenAI from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_wqDLmxGMRbmUrKtHE8ZWJc73FuzFzNT70ItXxJkE/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it OpenAI, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable OpenAI for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_wqDLmxGMRbmUrKtHE8ZWJc73FuzFzNT70ItXxJkE/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the OpenAI URL.
- Step 03
Save and start
Save the connection and enable OpenAI in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"openai": {
"url": "https://edge.vinkius.com/vk_preview_wqDLmxGMRbmUrKtHE8ZWJc73FuzFzNT70ItXxJkE/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using OpenAI
Open Agent mode in chat and ask: "Using OpenAI, help me...". 10 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"openai": {
"url": "https://edge.vinkius.com/vk_preview_wqDLmxGMRbmUrKtHE8ZWJc73FuzFzNT70ItXxJkE/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using OpenAI
Ask Copilot: "Using OpenAI, help me...". 10 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"openai": {
"url": "https://edge.vinkius.com/vk_preview_wqDLmxGMRbmUrKtHE8ZWJc73FuzFzNT70ItXxJkE/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using OpenAI
Open Cascade and ask: "Using OpenAI, help me...". 10 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"openai": {
"url": "https://edge.vinkius.com/vk_preview_wqDLmxGMRbmUrKtHE8ZWJc73FuzFzNT70ItXxJkE/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using OpenAI
Ask Cline: "Using OpenAI, help me...". 10 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add openai --transport http "https://edge.vinkius.com/vk_preview_wqDLmxGMRbmUrKtHE8ZWJc73FuzFzNT70ItXxJkE/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using OpenAI
Ask Claude: "Using OpenAI, show me...". 10 tools are ready
Where the request belongs
Work OpenAI can move forward.
This is for AI engineers building production-ready agents that need to perform real-world actions like image generation or safety checks. It's also for content creators who need to automate large-scale production workflows without manual copy-pasting.
AI Engineer
Building production agents that need to trigger image generation or content moderation in real-time.
Content Strategist
Automating large-scale text generation and structured data extraction for marketing campaigns.
Data Scientist
Managing embedding generation and fine-tuning workflows programmatically.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsGradient AI (LLM API & Finetuning)
Access powerful LLMs, fine-tune models on your own data, and generate embeddings directly through your AI agent.
DeepInfra (Serverless LLM Inference)
Run top-tier LLMs, image generation, and embeddings via DeepInfra's serverless infrastructure directly from your AI agent.
Together AI
Access 100+ open-source models for chat, image generation, and fine-tuning. Power your AI agents with Llama 3.3, Flux, and more.
Eden AI
Access 100+ AI models through a single API. route LLMs, generate embeddings, and execute specialized AI tasks like OCR and translation.
Mistral AI (Frontier LLMs & Embeddings)
Manage AI inference via Mistral. execute chat completions, generate RAG embeddings, and audit frontier models.
Mistral AI
Build with European open-weight language models that deliver strong reasoning, multilingual capability, and efficient inference.
Bring your own AI
Change the model, client or framework. Keep OpenAI connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about OpenAI.
The practical details behind the request, access and result.
Can the OpenAI MCP help me make images?
Yes, it lets your agent use DALL-E 3 to create images from text descriptions. It returns a URL you can use immediately in your app or workflow.
How does the OpenAI MCP handle safety?
It uses the official moderation capabilities to check your text for policy violations. Your agent can automatically flag and block unsafe content before it reaches your users.
Can I use this to train my own models?
Yes, you can use the fine-tuning capabilities to start and monitor custom training jobs. This lets your agent manage the lifecycle of your custom models without you needing to manually monitor them.
Does the OpenAI MCP work for structured data?
It's great for that. You can use the structured output capability to make sure your agent always gives you valid JSON, which is perfect for connecting to other software.
Can my agent see my existing assistants?
Yes, it can browse your configured OpenAI Assistants. This means your agent can identify and interact with the specific assistants you've already set up for different tasks.
Is this the right way to build a RAG system?
It's a key part of it. You can use the embedding capabilities to turn your data into vectors, which is the standard way to build semantic search.
Which models can I use?
Any model available on your API key: GPT-4o, GPT-4o-mini, GPT-4-turbo, o1, o3. use list_models to see all.
Can I generate images?
Yes! Use generate_image with a text prompt. Supports 1024x1024, 1792x1024, and 1024x1792 sizes.
How does content moderation work?
The moderate_content capability analyzes text against OpenAI's content policy, flagging categories like hate, violence, and self-harm with confidence scores.
One connection away
Give your agent a direct line to OpenAI.
Connect OpenAI once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available