Skip to content

LLM Configurator

by aikuba · remote · no sign-in to list tools · v1.0.0 · published by GitHub user aikuba

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

Changes · 2
CompareRegistry entry

5 tools: 2 change things and 3 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

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

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

5 tools

Changes things 2Claude Code: ask
  • check_hardware_fitUse this when the user asks whether one specific model runs on one specific machine, at what memory cost, and roughly how fast.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • models_for_hardwareUse this when the user asks what models a given machine can run.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
Only reads 3Claude Code: allow
  • compare_hardwareUse this when the user compares two to four machines.No findings

    Why it is in this group

    • The name "compare_hardware" says "compare": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • get_model_specsUse this when the user asks about one model's size, architecture, context window or licence.No findings

    Why it is in this group

    • The name "get_model_specs" says "get": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true
  • search_catalogUse this first when the user names a GPU, Mac, mini PC or language model and you need its id for the other tools.No findings

    Why it is in this group

    • The name "search_catalog" says "search": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: false
    • idempotentHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__llmconfigurator__search_catalog",
      "mcp__llmconfigurator__compare_hardware",
      "mcp__llmconfigurator__get_model_specs"
    ],
    "ask": [
      "mcp__llmconfigurator__check_hardware_fit",
      "mcp__llmconfigurator__models_for_hardware"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as llmconfigurator. Review it before you use it.