io.github.aikuba/llmconfigurator

up checked 2026-11-11T08:39:24.674Z

Unclaimed · Unverified

Publisher-provided title

LLM Configurator

Publisher-provided description

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

Summary by lookupd

Read-only lookup of local LLM fit on GPUs and Macs: VRAM needs, tokens per second, model specs and hardware comparisons.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http llmconfigurator https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp

Codex, remote (streamable-http)

codex mcp add llmconfigurator --url https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

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

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

search_catalog Use this first when the user names a GPU, Mac, mini PC or language model and you need its id for the other tools. Matches names and common aliases in a fixed ca
check_hardware_fit Use this when the user asks whether one specific model runs on one specific machine, at what memory cost, and roughly how fast. Needs a hardware id and a model
models_for_hardware Use this when the user asks what models a given machine can run. Needs a hardware id from search_catalog. Returns up to 20 catalogue models ranked for that mach
compare_hardware Use this when the user compares two to four machines. Needs hardware ids from search_catalog. Returns memory, bandwidth, memory type, release year, status and a
get_model_specs Use this when the user asks about one model's size, architecture, context window or licence. Needs a model id from search_catalog. Returns total and active para

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.aikuba/llmconfigurator.svg)](https://lookupd.com/servers/io.github.aikuba/llmconfigurator)