LLM Configurator

io.github.aikuba/llmconfiguratorVersion 1.0.0

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

Status

Responds322 msNov 14, 2026, 14:44 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 14:44 UTC
Latency: 322 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: Hosted outside the EU (detected)
Registry data as of: Nov 14, 2026, 22:14 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcpResponds322 msNov 14, 2026, 14:44 UTC

No sign-in

Claude Code

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

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: llmconfigurator
Remote MCP server URL: https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp

Cursor

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

VS Code

code --add-mcp '{"name":"llmconfigurator","type":"http","url":"https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

5 tools

Tools of LLM Configurator
	Description		Read-only	Idempotent	Open world
`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.	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.	No	Yes	Yes	No
`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.	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.	No	Yes	Yes	No
`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.	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.	No	Yes	Yes	No
`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.	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.	No	Yes	Yes	No
`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.	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.	No	Yes	Yes	No

Details

Registry status: Active
Published: Oct 2, 2026
Updated: Oct 2, 2026
Website: https://llmconfigurator.com/en/mcp⁠ (opens in a new tab)
Repository: https://github.com/aikuba/LLMconfigurator.com⁠ (opens in a new tab)
Categories (suggested): AI modelsSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing