Loading...
A simple MCP server that enables interaction with OpenAI assistants, providing tools to manage assistants and threads, and stream responses.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
A simple MCP server that enables interaction with OpenAI assistants, providing tools to manage assistants and threads, and stream responses.
This server provides useful tools for managing OpenAI assistants, but its safety relies heavily on the security of the OpenAI API key. It is safe to use within a controlled environment where the API key is protected. Risks increase if the API key is exposed or if the server is used with untrusted inputs.
Performance depends on the OpenAI API's response times and the complexity of the assistant's tasks. Streaming responses improve perceived performance.
Costs are primarily associated with OpenAI API usage, including token consumption and assistant runtime. Monitor API usage to avoid unexpected charges.
npx -y @smithery/cli install mcp-simple-openai-assistant --client claude{
"mcpServers": {
"openai-assistant": {
"command": "python",
"args": ["-m", "mcp_simple_openai_assistant"],
"env": {
"OPENAI_API_KEY": "your-api-key-here"
}
}
}
}OPENAI_API_KEYcreate_assistantCreates a new OpenAI assistant with specified name, instructions, and model.
Allows creation of new assistants, potentially consuming resources.
list_assistantsLists all available OpenAI assistants associated with the API key.
Read-only operation, no side effects.
retrieve_assistantRetrieves detailed information about a specific OpenAI assistant.
Read-only operation, no side effects.
update_assistantModifies an existing OpenAI assistant's name, instructions, or model.
Allows modification of assistant configurations, potentially impacting behavior.
create_new_assistant_threadCreates a new conversation thread with a user-defined name and description.
Creates new threads, potentially consuming resources.
list_threadsLists all locally managed conversation threads from the database.
Read-only operation, no side effects.
delete_threadDeletes a conversation thread from both OpenAI's servers and the local database.
Deletes threads, resulting in permanent data loss.
ask_assistant_in_threadSends a message to an assistant within a thread and streams the response back in real-time.
Sends messages and receives responses, potentially triggering unintended actions.
API Key
cloud
This server provides useful tools for managing OpenAI assistants, but its safety relies heavily on the security of the OpenAI API key. It is safe to use within a controlled environment where the API key is protected. Risks increase if the API key is exposed or if the server is used with untrusted inputs.
The level of autonomy depends on the permissions granted by the OpenAI API key and the specific tools used. Exercise caution when using destructive tools like `delete_thread`.
Production Tip
Implement robust error handling and monitoring to ensure the server's stability and performance in a production environment.
To provide a simple interface for interacting with OpenAI assistants through the Model Context Protocol.
By setting the `OPENAI_API_KEY` environment variable with your API key.
Use the `create_new_assistant_thread` tool to create a named thread.
Use the `list_threads` tool to list all managed threads and their IDs.
Use the `ask_assistant_in_thread` tool, providing the thread ID and your message.
The attacker could create, modify, and delete assistants and threads, potentially incurring costs and compromising data.
No, file uploads are not currently supported, but are listed as a TODO item.