LLM Configurator

io.github.aikubav1.0.0Updated Oct 2, 2026

Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.

VerifiedStreamable HTTPWeb executableAI & ML

Overview

AI-generated overview

Read-only lookup of which local LLMs a given GPU or Mac can run, including VRAM fit, tokens per second, and model specs.

What it does
This remote MCP server provides read-only reference information about running large language models locally. Based on the registry description, it answers questions about which local LLMs a particular GPU or Mac can run, whether a model fits in available VRAM, expected tokens per second, and model specifications. No tool list is published in the manifest, so the exact tool names and parameters are not documented here.
When to use it
Useful when planning local LLM deployment and you want a quick check of hardware compatibility, VRAM requirements, and rough performance expectations before downloading or running a model. It is a lookup aid rather than a tool that installs, downloads, or runs models.
Requirements
A remote streamable HTTP endpoint; no package installation is needed. The manifest declares no authentication, environment variables, or headers, so no credentials appear to be required. Network access to the provider's endpoint is needed.
Before you install
The manifest declares no authentication, environment variables, or headers, so no secrets are requested. The description indicates read-only reference data, but the tool list is not published, so verify actual behavior before relying on it. Queries are sent to a third-party remote endpoint.

Installation

In SourceWeft

  1. Open LLM Configurator in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "llmconfigurator": {
      "type": "http",
      "url": "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"
    }
  }
}

README

This repository has no README.

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 2, 2026