OpenAI

Bridges MCP clients with OpenAI Chat Completion and Assistants APIs, enabling management of assistants, files, and tools.

python

1

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You run a focused MCP server that bridges between MCP clients and OpenAI’s Chat Completion and Assistant capabilities. This server lets you manage assistants, upload files for context, and control which tools are available, all through a standardized MCP interface so your clients can interact with OpenAI securely and consistently.

How to use

Install and run the server, then connect your MCP client to it. You can start the server by providing your OpenAI API key either via an environment variable or as a direct command-line argument. Use the client to perform tasks like asking questions to models such as gpt-4 and gpt-3.5-turbo, managing assistants (create, list, retrieve, update, delete), and handling files associated with assistants (upload, list, delete). You can also enable or disable tools for each assistant, such as file_search, to tailor capabilities per assistant.

How to install

Prerequisites: ensure you have Python installed on your system.

Open a terminal. 2) Navigate to the project root where the MCP server package is located.
Install the server package in your environment.
Verify installation and readiness to start the server.

Additional setup and configuration

Run the server by supplying your OpenAI API key one of two ways. Set the environment variable OPENAI_API_KEY or pass the key as a command-line argument.

Environment variable method:

export OPENAI_API_KEY='your-api-key-here'
mcp-server-openai

Command-line argument method:

mcp-server-openai --openai-api-key 'your-api-key-here'

Available tools

ask-openai

Ask a direct question to a specified OpenAI model using the server's MCP interface.

list-assistants

Return a list of all assistants defined in the server.

retrieve-assistant

Fetch details for a specific assistant by its ID.

create-assistant

Create a new assistant with a name, instructions, and model settings.

update-assistant

Update properties of an existing assistant, such as name, instructions, or model.

delete-assistant

Remove an assistant by its ID.

upload-file

Upload a file to be associated with assistants for context or retrieval.

list-files

List all uploaded files available to assistants.

delete-file

Delete a file by its ID from the available files.