The OpenAI MCP for GPT, embeddings, and images in your automations
Connect your OpenAI API key once and chat completions, embeddings, image generation, and content moderation become workflow steps on a visual canvas.
What the OpenAI MCP connector does
The OpenAI connector for Mattering Automations ships four nodes: Chat Completion for text generation with GPT models, Embedding for turning text into vectors, Image Generation for OpenAI's image models, and Moderation for content policy classification.
Every node speaks MCP, the open protocol for connecting AI assistants to tools, so Claude, ChatGPT, and any MCP-capable assistant can use them, alongside Matter, the AI assistant built into the platform. An assistant can orchestrate a workflow that calls GPT for specific steps, mixing model providers inside one canvas.
Image generation has a platform twist: an optional store setting saves generated images straight into Mattering's managed file system, so downstream steps receive a stable file reference instead of megabytes of base64, and the image shows up in your platform files with its prompt recorded.
One connection, three surfaces
- Visual automations. Drag OpenAI nodes onto the canvas and wire them to triggers, conditions, and other apps.
- AI agents, yours or ours. These nodes speak MCP, the open protocol, so Claude, ChatGPT, and any MCP-capable assistant can use them, and Matter, the agent built into the platform, uses them natively.
- The whole platform. Combine with native tasks, projects, and other connectors, no middleware in between.
Every OpenAI node, ready to drop on the canvas
4 nodes, generated from the connector itself so this list always matches what ships. Expand a category to browse.
Action nodes 4
OpenAI Chat
Generate a chat completion with GPT models
OpenAI Embedding
Generate text embeddings
OpenAI Image
Generate images with OpenAI image models
OpenAI Moderation
Check text for content policy violations
Connecting OpenAI takes one credential
Create an API key at platform.openai.com under API keys. Keys start with sk-.
In the OpenAI platform, create an API key.
In Mattering Automations, open Connectors, choose OpenAI, and create a credential with the key.
The connector verifies the key against OpenAI's models endpoint.
All four OpenAI nodes appear in the canvas palette, ready to use.
Common uses for the OpenAI MCP
Text generation steps in any workflow
Drafts, rewrites, summaries, and structured extraction with a GPT model as one canvas node between your data source and its destination.
Embeddings for search and matching
Vectorize documents or tickets as they arrive and store the vectors, powering similarity matching and retrieval workflows.
Generated images that file themselves
Produce illustrations or social images and store them directly as Mattering platform files, with the prompt kept as provenance, ready to attach to tasks or content.
Moderation gates on user content
Screen inbound text through the moderation node and branch the workflow when something is flagged, before it ever reaches a public surface.
Cross-provider agent pipelines
Use GPT for some steps and Claude for others inside the same canvas, chosen per step, orchestrated by an MCP-connected assistant.
Example: Social images generated and filed on demand
Built on the Automations canvas in a few minutes, or described in plain language to Matter and built for you.
Trigger: a task tagged needs-image reaches Ready in Mattering Productivity.
OpenAI: Image Generation creates the visual from the task's brief, storing it as a platform file.
The workflow attaches the file reference back to the task and comments that the image is ready.
A reviewer approves it from the task card, with the generation prompt visible in the file's history.
OpenAI MCP questions, answered
Can an AI agent call GPT models through this MCP?
Yes. Matter and any MCP-connected assistant, including Claude and ChatGPT, can run chat completions, embeddings, image generation, and moderation through the same four nodes available on the automation canvas.
Does this work with Claude, ChatGPT, or other AI assistants?
Yes. Mattering exposes these nodes over MCP, an open protocol for connecting AI assistants to tools, so any MCP-capable assistant can connect to your workspace and use them. Matter, the assistant built into the platform, uses the same nodes natively.
Which models can the nodes use?
Any model your OpenAI API key can access; the model id is a per-node setting with sensible defaults (a current GPT model for chat, text-embedding-3-small for embeddings, gpt-image-1 for images).
Where do generated images go?
By default the node returns OpenAI's response directly. With the store option enabled, images are saved into Mattering's managed platform file system and the node outputs file references (id, size, storage location) instead of raw base64, which keeps workflow payloads small and makes the images browsable.
What credential does the connector use?
An OpenAI API key, sent as a bearer credential and stored encrypted in Google Secret Manager. Keys can be rotated at platform.openai.com and updated on the connector at any time.
What are the API rate limits?
OpenAI enforces per-organization rate limits that vary by model and usage tier; OpenAI's documentation is the source of truth for current numbers. The connector surfaces API errors on the node output so workflows can retry.
What is not supported?
The connector covers chat completions, embeddings, image generation, and moderation. Assistants API state, fine-tuning jobs, file management on OpenAI's side, and realtime audio are not exposed as nodes.
Put OpenAI to work inside your workspace
Connect once, then use every node in visual automations and AI agent workflows across the Mattering platform.
All product names, logos, and brands are property of their respective owners and are used for identification purposes only. Use of these names, logos, and brands does not imply endorsement or affiliation. OpenAI is a product of its respective owner; Mattering is an independent platform.