io.github.Daichi-Kudo/llm-advisor
llm-advisor-mcp
Real-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.
alive probed 2026-10-19
4tools
≈ 744tokens, estimate
≈ 0.4 %of Claude's 200k window
0.5×the median server
347 msto initialize
10 msto list tools
- Run it
- npx -y llm-advisor-mcp@0.4.5 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- llm-advisor-mcp 0.4.0
- Capabilities
- tools
- Instructions
- none
- Of a 1M window
- ≈ <0.1 % of a 1M context window, estimate
- Claude count
- The count_tokens endpoint refused the tool schemas: invalid x-api-key. The estimate stands in.
- Repository
- https://github.com/Daichi-Kudo/llm-advisor-mcp
- Registry
- active, updated 2026-06-17 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
Estimates with the o200k_base tokenizer.
| Tool | o200k estimate | Share of this server |
|---|---|---|
| recommend_model | 235 | 32 % |
| list_top_models | 197 | 26 % |
| get_model_info | 176 | 24 % |
| compare_models | 136 | 18 % |
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The Anthropic count_tokens endpoint refused the tool schemas (invalid x-api-key). A client that validates schemas can refuse them too.