XFMS - Xpansion Framework Model Source

**Pick the right LLM for any task.** XFMS infers which quality in its catalog against those dimensions, and returns a ranked shortlist with plain-English rationale per pick. The catalog updates continuously from **8 independent third-party evaluators** — no provider self-reports, no single-source benchmarks. Missing data is recorded as missing, not interpolated. **Three tools:** - `rank` — ranked shortlist with weights and rationale - `pick` — single best pick - `discover` — which quality dimensions matter, without ranking **No OpenRouter key needed.** The hosted endpoint covers inference; you only need a free XFMS access token from [xpansion .dev/xfms/get-started](https://xpansion.dev/xfms/get-started). Part of the [Xpansion Framework](https://xpansion.dev) — an enforcement layer for AI-assisted work.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 需 API Key（需要配置：apiKey）
端点: https://xfms.run.tools

该服务需要凭证，请按官方文档申请后替换占位符

{
  "mcpServers": {
    "XFMS - Xpansion Framework Model Source": {
      "headers": {
        "Authorization": "Bearer \u003cYOUR_KEY\u003e"
      },
      "url": "https://xfms.run.tools"
    }
  }
}

能力清单

工具	说明
rank	Rank LLMs for a stated purpose. Returns a shortlist with weights, scores, and plain-English rationale per pick. Use when the user wants to see and compare alternatives, not just one answer.
pick	Return the single best LLM for a stated purpose. Concise output, no list. Use when the user has settled on the criteria and just wants one answer.
discover	Show which quality dimensions matter for a stated purpose, WITHOUT ranking any models. Returns the inferred weights and the discovery-walk trace. Useful for understanding how XFMS interprets the purpose before committing to a pick.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。