ai
OpenAI MCP Integration for Vercel AI SDK
Connect OpenAI to Vercel AI SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.
Connect OpenAI to Vercel AI SDK
Use KosmoKrator as a local integration gateway for Vercel AI SDK agents and scripts.
Create an MCP client that starts or connects to the KosmoKrator gateway for the selected integration. The gateway is local, scoped to this integration, and starts with
--write=deny so Vercel AI SDK can inspect read-capable tools without receiving write access by default.
OpenAI MCP Config for Vercel AI SDK
Prefer CLI JSON calls when a workflow only needs one deterministic integration operation.
{
"mcpServers": {
"kosmokrator-openai": {
"type": "stdio",
"command": "kosmo",
"args": [
"mcp:serve",
"--integration=openai",
"--write=deny"
]
}
}
} Run the Gateway Manually
kosmokrator mcp:serve --integration=openai --write=deny Why Use KosmoKrator Here
Expose only OpenAI instead of a broad multi-service tool list.
Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.
Start read-only, then opt into ask or allow for trusted workspaces.
OpenAI Tools Visible to Vercel AI SDK
Vercel AI SDK sees stable MCP tool names generated from the OpenAI integration catalog.
| MCP tool | Source function | Type | Description |
|---|---|---|---|
integration__openai__openai_chat_completion | openai.openai_chat_completion | Write | Generate a chat completion using OpenAI GPT models. Send a conversation as an array of messages with role and content. |
integration__openai__openai_create_embedding | openai.openai_create_embedding | Write | Generate an embedding vector for text input using OpenAI embedding models. |
integration__openai__openai_create_image | openai.openai_create_image | Write | Generate an image from a text prompt using DALL·E. |
integration__openai__openai_transcribe_audio | openai.openai_transcribe_audio | Write | Transcribe audio into text using OpenAI Whisper. Supports MP3, MP4, WAV, M4A, and WEBM audio files. |
integration__openai__openai_text_to_speech | openai.openai_text_to_speech | Write | Generate speech audio from text using OpenAI TTS. Returns base64-encoded audio content. |
integration__openai__openai_create_assistant | openai.openai_create_assistant | Write | Create an OpenAI assistant with a model, name, instructions, and optional tools. |
integration__openai__openai_list_assistants | openai.openai_list_assistants | Read | List all OpenAI assistants available to the authenticated user. |
integration__openai__openai_create_thread | openai.openai_create_thread | Write | Create a conversation thread for the OpenAI Assistants API. Optionally include initial messages. |
integration__openai__openai_add_message_to_thread | openai.openai_add_message_to_thread | Write | Add a message to an existing conversation thread. |
integration__openai__openai_list_thread_messages | openai.openai_list_thread_messages | Read | List messages in an OpenAI conversation thread. |
integration__openai__openai_create_run | openai.openai_create_run | Write | Start an assistant run on a thread. Returns the run with its initial status. |
integration__openai__openai_get_run | openai.openai_get_run | Read | Get the status and details of an assistant run on a thread. |
integration__openai__openai_upload_file | openai.openai_upload_file | Write | Upload a file to OpenAI for use with Assistants, Fine-tuning, or Batch API. |
integration__openai__openai_list_files | openai.openai_list_files | Read | List files uploaded to OpenAI, optionally filtered by purpose. |
integration__openai__openai_list_models | openai.openai_list_models | Read | List all models available from OpenAI, including GPT, DALL·E, Whisper, and embedding models. |