Stipple — Reference Verification

Fact-check citations: resolve, match, support claims. Arithmetic rechecked. Free to start.

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
58%
命名品質
100%
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

~539Token(工具定義)
~1.6 KB典型回應大小
極小的注意力影響(128k 上下文的 0.42%)

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": {
    "openwarrant-verify": {
      "url": "https://www.stipple.sh/mcp-verify"
    }
  }
}

遠端端點

https://www.stipple.sh/mcp-verifystreamable-http

它能做什麼

工具清單

工具(1)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢verify_references(text, url, bytes_b64, filename, deep)

Fact-check a document's REFERENCES and CLAIMS — built for AI-generated reports whose citations must be checked before they're trusted. USE THIS WHEN someone shares a report, article, whitepaper, or deep-research export (or a link to one) and asks: is this accurate / legit? are these citations real? fact-check this. did the AI make this up? Also use it proactively before relying on any AI-written document. Provide the document ONE way: `url` (a public http(s) link to a PDF or web page — fetched server-side, the cheapest call: no need to download or encode anything), `text` (pasted markdown/plain prose), OR `bytes_b64` (a base64 PDF; URLs are read from the PDF's link annotations, so they're exact). Default (fast): provenance (is it a ChatGPT deep-research export?), citation resolution (live / archived / dead, papers matched against arXiv/Crossref to catch 'real ID, wrong paper'), and internal MATH (recompute the doc's own arithmetic). Set `deep=true` to also fetch each cited source and judge whether it SUPPORTS or CONTRADICTS the claim (slower, ~a minute). Returns a trust summary, per-item tables, and a shareable `permalink` to the public fact-check record. HONEST BOUNDARY: this reports verification COVERAGE, not truth — 'supported' means evidence-backed (not necessarily true) and 'unsupported' means no evidence found (not necessarily false). It tells a reviewer WHERE to look; it does not bless the document, and it never affects the fraud risk band.

輸入結構描述

{
  "type": "object",
  "properties": {
    "text": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Text"
    },
    "url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Url"
    },
    "bytes_b64": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Bytes B64"
    },
    "filename": {
      "default": "document.pdf",
      "title": "Filename",
      "type": "string"
    },
    "deep": {
      "default": false,
      "title": "Deep",
      "type": "boolean"
    }
  },
  "title": "verify_referencesArguments"
}

輸出結構描述

{
  "type": "object",
  "additionalProperties": true,
  "title": "verify_referencesDictOutput"
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本1 個工具
已驗證未記錄版本1 個工具