2origin vs Fetch
Сравнение двух MCP-серверов по фактам. Выбери подходящий для Claude Desktop, Claude Code или Cursor.
Benxiang Protocol · One Source, Infinite Shadows: Preserve the original form, project on demand. A persistent object representation layer for AI—AI only submits semantic transactions, which are validated by a deterministic compiler before being committed. Every field can answer "why". ShadowBench-W benchmark results (Run #27, post-probe fix, n=6 each): W3 state accuracy 95.8% vs bare model 52.1% vs vector RAG.
Сравнение
| Параметр | 2origin | Fetch |
|---|---|---|
| Цена | Free | Free |
| Установки | — | 1 |
| Рейтинг | — | — |
| Проверен | — | |
| Hosted | — | — |
| Инструменты | — | — |
| Категория | ai | ai |
| Автор | dongsheng123132 | Community |
| Репозиторий | dongsheng123132/2origin | modelcontextprotocol/servers |
Когда выбрать 2origin
Benxiang Protocol · One Source, Infinite Projections: Preserve the original form, project on demand. A persistent object representation layer for AI—AI submits only semantic transactions, which undergo deterministic compiler validation before materialization, with every field able to answer "why". ShadowBench-W benchmarks (Run #27, post-inquiry fixes, n=6 each): W3 state accuracy 95.8% vs bare model 52.1% vs vector RAG 58.3% (p=0.0024); state layer increments accumulate across entire documents, emerging from states never explicitly stated in any individual passage. Core shared across three dialects adds only 4 lines; 68 language-agnostic consistency vectors + two implementations.
Когда выбрать Fetch
Web content fetching and conversion for efficient LLM usage.
Ищешь что-то другое? Весь каталог MCP или в тренде на неделе.