Connect LLM Configurator and your agent gets 5 tools, among them check_hardware_fit, compare_hardware, get_model_specs. It answers at https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 2 October 2026; the last check, on 17 November 2026, succeeded.
Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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 id from search_catalog. Returns a fit verdict, the memory arithmetic, and a deco Inputs: hardware_id, model_id, quantisation, context_length |
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 dated price where one is recorded, side by side. A price of null means none is Inputs: hardware_ids |
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 parameters, weight size per quantisation, context length, licence, release date and Inputs: model_id |
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 machine, each with a fit verdict and a speed range, optionally filtered to one use s Inputs: hardware_id, quantisation, context_length, use_case, limit |
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 catalogue of local-LLM hardware and models. It does not return specs, fit or speed Inputs: query, kind, limit |
Every block below points at https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp. Pick your client and copy.
claude mcp add --transport http llm-configurator https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp
{
"mcpServers": {
"llm-configurator": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"]
}
}
}{
"mcpServers": {
"llm-configurator": {
"url": "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"
}
}
}{
"servers": {
"llm-configurator": {
"type": "http",
"url": "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"
}
}
}{
"context_servers": {
"llm-configurator": {
"url": "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"
}
}
}{
"mcpServers": {
"llm-configurator": {
"serverUrl": "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"
}
}
}{
"mcpServers": {
"llm-configurator": {
"url": "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"
}
}
}name: LLM Configurator
version: 0.0.1
schema: v1
mcpServers:
- name: LLM Configurator
type: streamable-http
url: https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp{
"mcpServers": {
"llm-configurator": {
"httpUrl": "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"
}
}
}{
"mcpServers": {
"llm-configurator": {
"type": "http",
"url": "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"
}
}
}{
"mcpServers": {
"llm-configurator": {
"url": "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"
}
}
}goose://extension?url=https%3A%2F%2Felgadmisijrfowuujcmu.supabase.co%2Ffunctions%2Fv1%2Fmcp&type=streamable_http&id=llm-configurator&name=LLM%20Configurator
It answered our last check on 17 November 2026 in 283 ms. Over 4 checks since 2 October 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
5, as returned by the server's own tools/list on 20 November 2026: check_hardware_fit, compare_hardware, get_model_specs, models_for_hardware, search_catalog.
It answered our last check on 17 November 2026 in 283 ms. Over 4 checks since 2 October 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.aikuba. Endpoint host: elgadmisijrfowuujcmu.supabase.co. ARD identifier: urn:air:io.github.aikuba:mcp:llmconfigurator.
First indexed 2 October 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.