LABSCO SUMMARY

The local thread database is what makes this more than an API wrapper: conversations get names instead of ids, and they are still there tomorrow.

OpenAI's Assistants API gives you thread ids, which are unusable from a chat client — nobody remembers which of two opaque strings held the conversation about the migration. Storing them locally with a name and a description turns threads into something you can ask for. The deletion path is the other detail done right: removing a thread from both sides together avoids the usual state where the local list shows conversations that no longer exist upstream. Understand the shape: this reaches a second model from inside your client, so a call here is a call you pay OpenAI for, on top of whatever is running the client.

What it is

A client for OpenAI's Assistants API with a local thread store on top: create and modify assistants, and keep named persistent conversations that survive the session.

What you get

create_assistant, list_assistants, retrieve_assistant and update_assistant cover the assistant itself — name, instructions and model can be changed after creation.
Threads are named and described rather than referred to by id: create_new_assistant_thread takes a name, list_threads reads them from the local database, and update_thread renames one.
ask_assistant_in_thread sends a message into a specific thread and streams the reply back, so context accumulates where you put it.
delete_thread removes the conversation from OpenAI's servers and the local database together, rather than leaving one of the two behind.

Requirements

An OpenAI API key in OPENAI_API_KEY, and Python: install the package with pip and your client launches it as python -m mcp_simple_openai_assistant. Usage bills against your own OpenAI account.

Setup effort

One command plus a key — pip install mcp-simple-openai-assistant, then supply credentials

See installation options

USE CASES

01

Keeping a long-running conversation with a specialised assistant

Create the assistant with its instructions, open a named thread for the topic, and come back to it later by name instead of by id.

create_assistantcreate_new_assistant_threadask_assistant_in_threadlist_threads

02

Getting a second model's read without leaving your client

Send the question into the thread and stream the answer back, with the context of everything already asked in it.

ask_assistant_in_threadlist_assistantsretrieve_assistant

03

Adjusting an assistant that is not quite right

Change its instructions or model in place rather than creating a new one and losing the threads attached to it.

update_assistantretrieve_assistant

04

Clearing out what you are done with

Rename the threads worth keeping and delete the rest from OpenAI and the local store in one call.

update_threaddelete_threadlist_threads

9 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`ask_assistant_in_thread`

Sends a message to an assistant within a specific thread and streams the response. This provides progress updates and the final message in a single call.

Use this to continue a conversation with an assistant in a specific thread. The thread ID can be retrieved from the list_threads tool. The assistant ID can be retrieved from the list_assistants tool. Threads are not inherently linked to a particular assistant, so you can use this tool to talk to any assistant in any thread.

BEFORE YOU INSTALL

What to know first

Tools you get

9 tools when we connected. update_thread, which renames or re-describes a stored thread, is undocumented.

Requires

Python with pip
OPENAI_API_KEY in your environment

Where it runs

Both documented setups run the server on your machine.

CONTEXT COST

Light Standing cost

Rated by the size of the 9 tool definitions that ride along on every turn, not by how many there are

INSTALLATION

Connect your client

Server setup

TERMINAL

pip install mcp-simple-openai-assistant

MCP Clients

Claude Desktop — macOS

CLAUDE DESKTOP — MACOS · JSON

{
  "mcpServers": {
    "openai-assistant": {
      "command": "python",
      "args": [
        "-m",
        "mcp_simple_openai_assistant"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

Claude Desktop — Windows

CLAUDE DESKTOP — WINDOWS · JSON

{
  "mcpServers": {
    "openai-assistant": {
      "command": "C:\\Users\\<YOUR_USERNAME>\\AppData\\Local\\Programs\\Python\\Python311\\python.exe",
      "args": [
        "-m",
        "mcp_simple_openai_assistant"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

MCP Simple OpenAI Assistant

The local thread database is what makes this more than an API wrapper: conversations get names instead of ids, and they are still there tomorrow.

What it is

What you get

Requirements

Setup effort

Keeping a long-running conversation with a specialised assistant

Getting a second model's read without leaving your client

Adjusting an assistant that is not quite right

Clearing out what you are done with

9 tools

`ask_assistant_in_thread`

`create_assistant`

`create_new_assistant_thread`

`delete_thread`

`list_assistants`

`list_threads`

`retrieve_assistant`

`update_assistant`

`update_thread`

What to know first

Tools you get

Requires

Where it runs

Light Standing cost

Connect your client

Server setup

MCP Clients

Claude Desktop — macOS

Claude Desktop — Windows

MCP Simple OpenAI Assistant

The local thread database is what makes this more than an API wrapper: conversations get names instead of ids, and they are still there tomorrow.

What it is

What you get

Requirements

Setup effort

Keeping a long-running conversation with a specialised assistant

Getting a second model's read without leaving your client

Adjusting an assistant that is not quite right

Clearing out what you are done with

9 tools

ask_assistant_in_thread

create_assistant

create_new_assistant_thread

delete_thread

list_assistants

list_threads

retrieve_assistant

update_assistant

update_thread

What to know first

Tools you get

Requires

Where it runs

Light Standing cost

Connect your client

Server setup

MCP Clients

Claude Desktop — macOS

Claude Desktop — Windows

Same category

OpenAI MCP Server by mzxrai

OpenAI Assistant MCP Server

Atlas Cloud MCP Server (Image / Video / LLM APIs)

Gemini CLI MCP by blesscat

`ask_assistant_in_thread`

`create_assistant`

`create_new_assistant_thread`

`delete_thread`

`list_assistants`

`list_threads`

`retrieve_assistant`

`update_assistant`

`update_thread`