LLM Configurator MCP Server

by aikuba Your server? Claim it

answering

LLM Configurator is answering right now. Last checked 5 min ago. It exposes 5 tools.

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

The linked repository no longer exists on GitHub — it was deleted or made private.

Uptime history 14 days of history · worst day 99%

14 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

301 ms

Response time

average over 24h

open, no key

Access

streamable-http

This one has been quiet for a while

Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 5 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

[mcp_servers.llmconfigurator]
url = "https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"

.cursor/mcp.json

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

.vscode/mcp.json

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

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

catalog

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, and it does not search the web.

compare

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 on record. It does not check any model against the machines; use check_hardware_fit for that.

hardware

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 decode-speed range with a confidence label. Memory is sized from all parameters, speed from active parameters. It does not recommend purchases and does not run anything.

model

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 sources. It does not say whether the model fits any machine; use check_hardware_fit for that.

models

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 such as coding. It covers only models in the catalogue, at one quantisation and context length per call, and leaves out models that do not fit.

Endpoints

URL	Transport	State	Latency	Checked
https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp	streamable-http	answering	360 ms	5 min ago

Alternatives to LLM Configurator

same job, measured the same way

Nodegrove VRAM: can I run it?

by nodegrove

Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.

262 installs/wk 6 tools answering

Vllm Ops MCP

by jaimenbell

Read-only ops/health MCP server for a local vLLM instance: health tiers, GPU/VRAM, service status.

89 installs/wk local only

StudioTV LLM VRAM Calculator

by studiotvai

Does an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.

answering

Gguf MCP

by arose26

Inspect local GGUF/safetensors models: quantization, params, VRAM fit — headers only.

26 installs/wk local only

Onion Search

by farbodghasemlu

Local, read-only onion search and text retrieval over Tor with content filtering.

local only

mcp-usage

by rixtayz

Find out which MCP servers you actually use: local, read-only audit of Claude Code transcripts.

47 installs/wk local only

AI Compute Radar

by aicomputeradar

Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.

5 tools answering

OddsRelay

by oddsrelay

Read-only MCP server for OddsRelay odds data, with a token cap on every call that spends tokens.

347 installs/wk local only

LLM Configurator — questions

Answers built from our own checks of this server.

What can LLM Configurator do?

It exposes 5 tools, read directly from the server on our last check. Among them: check_hardware_fit, compare_hardware, get_model_specs, models_for_hardware, search_catalog. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is LLM Configurator working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 301 ms. The bar chart above shows every period we have measured.

Is LLM Configurator still maintained?

The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.

How do I connect LLM Configurator?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does LLM Configurator need an API key?

No. LLM Configurator completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is LLM Configurator?

It answers our handshake in 301 ms on average, which is faster than 44% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.