Quelllm MCP
Answers "will this model run on my GPU, and what would it cost?" — the quelllm.fr catalogue of open-weights LLMs, with VRAM and cost maths built in.Read full description
MGM-FALCONLABSCO SUMMARY
One model asking another, nothing more.
This is the smallest useful shape of a cross-vendor bridge: no routing, no cost controls, no conversation state — a prompt goes to OpenAI and the answer comes back. Usage bills to your own OpenAI key, so treat it as a second meter running alongside the first.
What it is
A minimal MCP server that lets Claude query OpenAI models directly over the Model Context Protocol. It is a single-purpose bridge: the prompt goes out through your OpenAI key and the response comes back into the conversation.
What you get
- A second model's answer available inside the first model's conversation, for comparison or a second opinion
- A small enough codebase to read end to end before you trust it with a key — install is
pip install -e .from a clone - A pytest check that exercises a real API call, so you can confirm the key and the wiring before connecting a client
Requirements
An OpenAI API key in OPENAI_API_KEY, and PYTHONPATH pointed at the checkout, both set in the client's server entry. It launches as python -m src.mcp_server_openai.server. The pyproject names the package mcp-server-openai at 0.1.0, with the console script mcp-server-openai. MIT licensed.
Setup effort
Build from source — clone the repository, then follow the project's own run instructions
USE CASES
01
Getting a second opinion mid-conversation
Send the same question to an OpenAI model and compare its answer against the one you already have.
02
Checking how another model words something
Pass a draft through a different model and read the difference, without switching applications.
03
Confirming a key works before wiring a client
Run the bundled test from the project root and read the sample response it prints.
BEFORE YOU INSTALL
What to know first
Requires
- python on PATH
- OPENAI_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
python -m src.mcp_server_openai.serverMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"openai-server": {
"command": "python",
"args": [
"-m",
"src.mcp_server_openai.server"
],
"env": {
"PYTHONPATH": "<YOUR_PATH_TO_MCP_SERVER_OPENAI>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}
