OpenAI

AI research and deployment company providing powerful language models and APIs that enable developers to build intelligent applications with natural language understanding and generation.

OpenAI MCP, Integrations & Automations for Enterprise AI Agents

Connect your AI agents to OpenAI MCP in minutes. No field mapping. No code required. Adopt AI's zero-shot API discovery means your agents understand OpenAI's schema on first contact - and can act on it instantly.

Generate MCP URL

What Your AI Agents Can Do

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Oai Delete Model on OpenAI

Deletes a fine-tuned model by id.

Oai Transcribe Audio on OpenAI

Transcribes audio to text (Whisper). Requires multipart file in real clients; this tool accepts JSON metadata only—use file_id from OAI_UPLOAD_FILE with purpose assist for pre-uploaded audio.

Oai Attach Assistant File on OpenAI

Attaches an uploaded file id to an assistant for retrieval. Use after OAI_UPLOAD_FILE.

Oai Create Thread And Run on OpenAI

Creates a new thread and run in one call (assistant_id required, optional thread messages JSON).

Oai Moderate Content on OpenAI

Classifies content against OpenAI moderation policy. Returns category scores.

Oai Delete Assistant on OpenAI

Deletes an assistant.

Oai Speech Opus on OpenAI

TTS preset returning opus format for low-latency playback. Same as OAI_TEXT_TO_SPEECH with response_format opus.

Oai Chat Reproducible on OpenAI

Chat completion with integer seed for more reproducible sampling. Returns standard completion object. Use when debugging or A/B testing prompts. For production diversity omit seed and use OAI_CHAT_COMPLETION.

Oai Chat Stream on OpenAI

Calls chat completions with stream true (SSE). Note: this MCP returns the first chunk as JSON text, not a live stream to the user. Use when integrating streaming clients; for full non-stream responses use OAI_CHAT_COMPLETION.

Oai Submit Tool Outputs on OpenAI

Submits tool outputs to continue a run waiting on tool_calls.

Oai Update Message on OpenAI

Updates message metadata.

Oai Get Thread on OpenAI

Gets thread metadata.

Oai Update Thread on OpenAI

Updates thread metadata or tool_resources.

Oai Vary Image on OpenAI

Creates variations of an image (multipart). Use for exploring alternatives to a seed image. Same limitation as OAI_EDIT_IMAGE for MCP binary upload.

Oai List Files on OpenAI

Lists uploaded files with optional purpose filter. Returns file metadata array. Use to find ids for OAI_GET_FILE or vector store attachment.

Oai Delete Thread on OpenAI

Deletes a thread and its messages.

Oai Cancel Batch on OpenAI

Cancels a batch.

Oai List Messages on OpenAI

Lists messages in a thread.

Oai List Runs on OpenAI

Lists runs for a thread.

Oai Create Batch on OpenAI

Creates a Batch API job from a JSONL input file id. Returns batch id.

Oai List Finetune Checkpoints on OpenAI

Lists checkpoints for a fine-tuning job.

Oai Translate Audio on OpenAI

Translates spoken audio to English text. Same multipart constraint as OAI_TRANSCRIBE_AUDIO.

Oai Upload File on OpenAI

Uploads a file (multipart). Pass file_path on the server filesystem, purpose (fine-tune, assistants, batch, vision). Returns file id and bytes. Use before fine-tuning or Assistants file search.

Oai Embed Small 512 on OpenAI

Embedding preset using text-embedding-3-small with dimensions=512 for smaller vectors. Use when storage cost matters.

Oai Image Hd Quality on OpenAI

Image generation preset with quality=hd for DALL·E 3. Returns high-detail images. Use when standard quality is insufficient.

Oai Get File Batch on OpenAI

Gets vector store file batch status.

Oai Vector Batch And Wait on OpenAI

Polls OAI_GET_FILE_BATCH until completed/failed/cancelled.

Oai Create Finetune on OpenAI

Creates a fine-tuning job from a training file id. Returns job id and status. Use OAI_LIST_FINETUNES to monitor.

Oai Batch Embeddings on OpenAI

Embeddings with input forced to JSON array of strings (batch). Returns multiple embedding objects in data. Use when embedding many snippets in one request.

Oai Update Run on OpenAI

Updates run metadata.

Oai Create Vector Store on OpenAI

Creates a vector store for file search. Returns id.

Oai Delete Vector Store File on OpenAI

Removes a file from a vector store.

Oai List Finetune Events on OpenAI

Lists events for a fine-tuning job (metrics, checkpoints).

Oai Get Vector Store on OpenAI

Gets vector store by id.

Oai Get Finetune And Wait on OpenAI

Polls OAI_GET_FINETUNE until terminal status (succeeded/failed/cancelled) or max_wait_ms. Returns final job object.

Oai List Run Steps on OpenAI

Lists steps for a run (tool calls, messages).

Oai Delete Vector Store on OpenAI

Deletes a vector store.

Oai Get Run Step on OpenAI

Gets a single run step.

Oai Create File Batch on OpenAI

Creates a batch attach job for many files to a vector store.

Oai Delete Assistant File on OpenAI

Removes a file attachment from an assistant (does not delete the file from storage).

Oai List Batches on OpenAI

Lists batches.

Oai Delete Message on OpenAI

Deletes a message.

Oai Text To Speech on OpenAI

Converts text to speech audio (JSON body). Returns binary; MCP surfaces JSON error if non-JSON response. Prefer model tts-1 or tts-1-hd.

Oai Chat Logprobs on OpenAI

Chat completion with logprobs enabled for token-level likelihoods. Returns logprob content in response. Use for debugging model uncertainty; omit for OAI_CHAT_COMPLETION.

Oai Cancel Run on OpenAI

Cancels an in-progress run.

Oai Chat Completion on OpenAI

Creates a chat completion with full control (model, messages, temperature, max_tokens, tools, tool_choice, response_format, stream, seed, logprobs). Returns assistant message(s), usage, and optional tool_calls. Use for general chat or when you need every OpenAI parameter. For JSON-only output use OAI_CHAT_JSON_MODE. For streaming SSE use OAI_CHAT_STREAM.

Oai Chat JSON Mode on OpenAI

Forces response_format type json_object so the model returns parseable JSON in message.content. Returns same shape as chat completions plus usage. Use when you need structured extraction; validate JSON client-side. For arbitrary chat without JSON guarantee use OAI_CHAT_COMPLETION.

Oai Cancel Finetune on OpenAI

Cancels a running fine-tune job.

Oai List Assistant Files on OpenAI

Lists files attached to an assistant (knowledge retrieval). Returns file ids and statuses. Use before detaching with OAI_DELETE_ASSISTANT_FILE.

Oai Create Assistant on OpenAI

Creates an Assistant (v2) with model, instructions, tools. Returns assistant id.

Oai List Models on OpenAI

Lists models available to the key. Returns id, owned_by, created.

Oai Add File To Vector Store on OpenAI

Attaches a file to a vector store.

Oai Update Vector Store on OpenAI

Updates vector store name or expiration.

Oai Image Multi Count on OpenAI

Image generation with n>1 for multiple candidates (DALL·E 2 style counts). Returns multiple image objects.

Oai List Finetunes on OpenAI

Lists fine-tuning jobs with pagination. Returns job statuses. Use after OAI_CREATE_FINETUNE.

Oai Create Thread on OpenAI

Creates a thread with optional initial messages JSON.

Oai Create Run on OpenAI

Starts a run for an assistant on a thread.

Oai Edit Image on OpenAI

Edits an image with a mask (multipart upload). Returns revised images. Use when inpainting; requires source PNG and mask. For variations without prompt-based edit use OAI_VARY_IMAGE.

Oai Get Finetune on OpenAI

Gets one fine-tuning job by id including fine_tuned_model when succeeded.

Oai Create Message on OpenAI

Adds a message to a thread (user/assistant). content can be string or JSON for multimodal.

Oai List Vector Store Files on OpenAI

Lists files in a vector store.

Oai Get File on OpenAI

Retrieves file metadata by id. Returns bytes, purpose, status. Use before downloading content.

Oai Get Batch on OpenAI

Gets batch status and output file ids when completed.

Oai Delete File on OpenAI

Deletes a file by id. Returns deleted:true. Use to clean up after fine-tune or failed uploads.

Oai Get File Content on OpenAI

Downloads raw file bytes (text or binary as string). Use for small text training files.

Oai Embedding Base64 on OpenAI

Embeddings with encoding_format base64 for smaller payloads over the wire. Returns base64-encoded vectors. Use when float arrays are too heavy; decode client-side.

Oai Get Batch And Wait on OpenAI

Polls OAI_GET_BATCH until completed/failed/cancelled/expired.

Oai Create Embedding on OpenAI

Creates embeddings for input string or array of strings. Returns embedding vectors and usage tokens. Use for semantic search pipelines. For many chunks in one call use OAI_BATCH_EMBEDDINGS.

Oai Update Assistant on OpenAI

Updates assistant fields partially.

Oai Create Run And Poll on OpenAI

Creates a run then polls OAI_GET_RUN until completed/failed/cancelled/expired or timeout. Returns final run.

Oai Get Model on OpenAI

Retrieves one model descriptor.

Oai Get Message on OpenAI

Gets one message.

Oai Completion on OpenAI

Legacy text completions (not chat) for a single prompt string. Returns choices with text and usage. Use only for legacy models; prefer OAI_CHAT_COMPLETION for instruct models.

Oai Get Assistant on OpenAI

Retrieves assistant by id.

Oai List Assistants on OpenAI

Lists assistants with pagination.

Oai Chat With Tools on OpenAI

Same endpoint as OAI_CHAT_COMPLETION but expects tools as a JSON string and sets tool_choice to auto unless overridden. Returns completion with possible tool_calls for agent loops. Use when the model must call functions. For plain text without tools use OAI_CHAT_COMPLETION.

Oai Get Run on OpenAI

Gets run status and usage.

Oai Upload And Attach Vector File on OpenAI

Composite: OAI_UPLOAD_FILE from file_path then OAI_ADD_FILE_TO_VECTOR_STORE. Returns both responses.

Oai Generate Image on OpenAI

Generates images from a text prompt (DALL·E 3 / 2). Returns b64_json or url per response_format. Use for creative assets. For edits use OAI_EDIT_IMAGE.

Oai List Vector Stores on OpenAI

Lists vector stores.

Connect OpenAI MCP using Adopt AI in 3 Simple Steps

Run a single command in your terminal to install the OpenAI MCP server locally, no complex setup, no cloud dependency.
A browser window opens automatically, where you can securely authenticate with your OpenAI account with one click.
Restart your AI client, and your agents instantly have full access to models, completions, embeddings, and every OpenAI object, ready to read, write, and automate.

Use Cases for OpenAI MCP

1. Intelligent Content Generation

AI agents call OpenAI models to generate marketing copy, documentation, email drafts, and reports, integrating generated content directly into connected workflows.

2. Automated Data Extraction & Summarization

AI agents use OpenAI to parse unstructured data � emails, PDFs, transcripts � extract key information, and produce structured summaries for downstream processing.

3. Conversational AI & Chatbot Workflows

AI agents leverage OpenAI's chat models to power customer-facing chatbots, internal helpdesks, and conversational interfaces across your tech stack.

4. Code Generation & Review

AI agents use OpenAI to generate code snippets, review pull requests, suggest refactors, and document functions, accelerating developer productivity.

5. Embedding & Classification Pipelines

AI agents call OpenAI embedding and classification APIs to power semantic search, content categorization, and sentiment analysis across enterprise data.

Explore Similar Apps

Cohere

Anthropic

Hugging Face

Frequently Asked Questions

Do I need my own developer credentials to use OpenAI MCP with Adopt AI?

No, you can get started immediately using Adopt AI's built-in OpenAI integration. For production use, we recommend configuring your own API keys for greater control and security.

Can I connect OpenAI with other apps through Adopt AI?

Yes! Adopt AI supports multi-app workflows, so your AI agents can seamlessly move data between OpenAI and CRMs, databases, content platforms, and more.

Is Adopt AI secure?

Absolutely. Adopt AI is SOC 2 Type 2 certified and ISO/IEC 27001 compliant, and adheres to EU GDPR, CCPA, and HIPAA standards. All data is encrypted in transit and at rest, ensuring the confidentiality, integrity, and availability of your data. Learn more here.

What happens if the OpenAI API changes?

Adopt AI maintains and updates all integrations automatically, so your agents always work with the latest API versions, no manual maintenance required.

Do I need coding skills to set up the OpenAI integration?

Not at all. Adopt AI's zero-shot API discovery means your agents understand OpenAI's schema on first contact. Setup takes minutes with no code required.

How do I set up custom OpenAI MCP in Adopt AI?

For a step-by-step guide on creating and configuring your own OpenAI API keys with Adopt AI, see here.