io.github.aikuba/llmconfigurator
LLM Configurator
io.github.aikuba/llmconfigurator costs 1 230 tokens of context per session. It has 5 tool definitions. That is 0.6 % of a 200k window. Measured 2026-10-03.
Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
alive probed 2026-10-03 · HTTP 200
5tools
1.2ktokens for the tool definitions
0.6 %of a 200k context window
993 msto initialize
849 msto list tools
- Endpoint
- https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp (streamable-http)
- Host
- elgadmisijrfowuujcmu.supabase.co
- Protocol
- 2025-11-25
- Reports itself as
- llmconfigurator 1.0.0
- Capabilities
- tools
- Instructions
- 375 characters
- Repository
- https://github.com/aikuba/LLMconfigurator.com
- Website
- https://llmconfigurator.com/en/mcp
- Registry
- active, updated 2026-10-02 · registry entry
- Reachable
- 2 of the last 2 probes
Most expensive tools
| Tool | Tokens | Share of this server |
|---|---|---|
| models_for_hardware | 373 | 30 % |
| check_hardware_fit | 339 | 28 % |
| search_catalog | 219 | 18 % |
| compare_hardware | 161 | 13 % |
| get_model_specs | 138 | 11 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Tokens |
|---|---|---|---|---|
| 2026-10-03 20:36 | alive | 993 ms | 5 | 1.2k |
| 2026-10-03 17:52 | alive | 449 ms | 5 | 1.2k |
Badge
[](https://mcp-pulse.ulehla.dev/s/io.github.aikuba/llmconfigurator)