MCP Simple OpenAI Assistant
by andybrandt
A simple MCP server for interacting with OpenAI assistants. It allows tools like Claude Desktop to create and interact with OpenAI assistants through the Model Context Protocol.
Last updated: N/A
What is MCP Simple OpenAI Assistant?
This is an MCP server that enables interaction with OpenAI assistants. It facilitates the creation, manipulation, and communication with OpenAI assistants through the Model Context Protocol, primarily designed for use with tools like Claude Desktop.
How to use MCP Simple OpenAI Assistant?
First, install the server using pip install mcp-simple-openai-assistant. Then, configure the server with your OpenAI API key in the environment. For Claude Desktop, add the server configuration to your Claude Desktop config file (example configurations for MacOS and Windows are provided in the README). Once configured, you can use the server to create, list, modify assistants, start conversation threads, send messages, and receive responses.
Key features of MCP Simple OpenAI Assistant
Create and manipulate OpenAI assistants
Start conversation threads
Send messages and receive responses
Workaround for long OpenAI responses to avoid client timeouts
Use cases of MCP Simple OpenAI Assistant
Integrating OpenAI assistants with Claude Desktop
Providing a simple interface for interacting with OpenAI assistants
Automating interactions with OpenAI assistants
Enabling other tools to leverage OpenAI assistants
FAQ from MCP Simple OpenAI Assistant
What is an MCP server?
What is an MCP server?
MCP stands for Model Context Protocol. It's a protocol that allows different tools to communicate with each other, in this case, Claude Desktop and the OpenAI API.
Why do I need this server?
Why do I need this server?
This server provides a way for tools like Claude Desktop to easily interact with OpenAI assistants without directly managing the OpenAI API.
How do I get an OpenAI API key?
How do I get an OpenAI API key?
You need to sign up for an OpenAI account and generate an API key from their platform.
What if I don't use Claude Desktop?
What if I don't use Claude Desktop?
While primarily designed for Claude Desktop, the server can potentially be adapted for use with other tools that support the Model Context Protocol.
What if I encounter timeouts with long OpenAI responses?
What if I encounter timeouts with long OpenAI responses?
The server implements a two-stage approach to handle long responses, but further improvements are planned to better manage timeouts.