GroundedKit Marketing Stats Checker

Check marketing and influencer stats against primary sources: verdict, source, safe wording.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
86%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~881token 数(工具定义)
~694 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 0.69%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "marketing-stats": {
      "url": "https://groundedkit.com/mcp"
    }
  }
}

远程端点

https://groundedkit.com/mcpstreamable-http

它能做什么

工具清单

工具(5)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢check_stat(text)

Paste a marketing or influencer-marketing statistic (a sentence or a whole paragraph), or ask for a reference number (e.g. 'what share of US adults use TikTok'). Returns the best-matching checked claim with its verdict, confidence, primary source, what the source actually says, a safe rephrasing and the claim URL, plus its kind (stat_check or reference_fact), as_of date, last_checked date and stale flag (last checked more than 180 days ago), and close alternatives. Returns match: none when the stat is not in the database.

输入模式

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The statistic as you saw it, e.g. 'influencer marketing returns $5.78 per $1'"
    }
  },
  "required": [
    "text"
  ]
}
🟢verify_text(text, max_statements)

Paste a whole draft (up to 20,000 characters: a blog post, deck notes, an email, a social caption). Splits it into sentences, keeps each sentence that contains a number or statistic, and matches each one against the checked claims. Returns one row per statement with the numbers found, the match level, verdict, safe rephrasing and claim URL, or status not_in_database, plus counts by status and verdict. Unmatched statistic text is logged anonymously (date and text only) to guide which stats get checked next.

输入模式

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The draft to check, up to 20,000 characters. Longer input is cut at 20,000 characters and flagged as truncated."
    },
    "max_statements": {
      "type": "integer",
      "minimum": 1,
      "maximum": 60,
      "default": 40,
      "description": "Maximum statements to check, 1 to 60 (default 40)"
    }
  },
  "required": [
    "text"
  ]
}
🟢search_claims(query, verdict, limit)

Keyword search over all checked marketing statistics (claim text, common phrasing, origin publisher). Optionally filter by verdict. Returns short summaries; get_claim returns the full record for an id.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Words or numbers to search for, e.g. 'email ROI' or 'trust influencers'. Empty string lists everything."
    },
    "verdict": {
      "type": "string",
      "enum": [
        "verified",
        "misquoted",
        "outdated",
        "unsourced"
      ],
      "description": "Optional verdict filter"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "Maximum results, 1 to 50 (default 10)"
    }
  },
  "required": [
    "query"
  ]
}
🟢get_claim(id)

Full record for one checked claim by id (slug) or claim page URL: verdict, confidence, origin, exact quote, method and sample, drift, publisher interest, safe rephrasing and every source we opened.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Claim id/slug, e.g. 'email-marketing-roi-36-to-1', or its groundedkit.com URL"
    }
  },
  "required": [
    "id"
  ]
}
🟢list_verdicts

The four verdicts (verified, misquoted, outdated, unsourced) with definitions and how many claims carry each, plus confidence levels and dataset info.

输入模式

{
  "type": "object",
  "properties": {}
}

社区

评价此服务器

证据

最近观测

已验证未记录版本5 个工具