ai
OpenAI MCP Integration for Claude Agent SDK
Connect OpenAI to Claude Agent SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.
Connect OpenAI to Claude Agent SDK
Give Claude Agent SDK workflows access to KosmoKrator integrations through a local MCP server.
Add a KosmoKrator stdio MCP server to the Claude Agent SDK options. The gateway is local, scoped to this integration, and starts with
--write=deny so Claude Agent SDK can inspect read-capable tools without receiving write access by default.
OpenAI MCP Config for Claude Agent SDK
Use a narrow integration list so the agent does not load unrelated tools.
{
"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 Claude Agent SDK
Claude Agent 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. |