MCP MeasureMCP Measure

索引已觀測

RealRun

Independent test scores for AI models on everyday tasks: inbox, scheduling, receipts.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
83%
命名品質
95%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~505Token（工具定義）
~871 B典型回應大小
極小的注意力影響（128k 上下文的 0.39%）

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案：

{
  "mcpServers": {
    "realrun": {
      "url": "https://realrun.baseledgerip.com/mcp"
    }
  }
}

遠端端點

https://realrun.baseledgerip.com/mcpstreamable-http

它能做什麼

工具清單

工具（4）

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢list_tasks

List the everyday tasks RealRun has tested AI models on, with item counts, test dates, results pages and playbook prices.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_scores(task)

Headline scores for every model RealRun tested on a task, best first, with cost tier and the metric definition.

輸入結構描述

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "enum": [
        "inbox-triage",
        "meeting-scheduling",
        "receipts",
        "finance",
        "support-replies"
      ],
      "description": "Task id, e.g. 'receipts'. See list_tasks."
    }
  },
  "required": [
    "task"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢recommend_model(task, priority, include_subscription)

Recommend which AI model to use for a task given a priority: 'accuracy', 'cost' or 'balanced'. Never recommends models RealRun flagged as not recommended.

輸入結構描述

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "enum": [
        "inbox-triage",
        "meeting-scheduling",
        "receipts",
        "finance",
        "support-replies"
      ],
      "description": "Task id, e.g. 'receipts'. See list_tasks."
    },
    "priority": {
      "default": "balanced",
      "description": "What matters most.",
      "type": "string",
      "enum": [
        "accuracy",
        "cost",
        "balanced"
      ]
    },
    "include_subscription": {
      "default": true,
      "description": "Include Claude models (tested on a subscription, no metered cost).",
      "type": "boolean"
    }
  },
  "required": [
    "task"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_warnings(task)

Models RealRun flagged as not recommended or needing caution on a task (scam failures, invented data, inconsistency).

輸入結構描述

{
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "enum": [
        "inbox-triage",
        "meeting-scheduling",
        "receipts",
        "finance",
        "support-replies"
      ],
      "description": "Task id, e.g. 'receipts'. See list_tasks."
    }
  },
  "required": [
    "task"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本4 個工具