DraftCheck AI-writing linter
DraftCheck: flags AI-writing patterns in prose with fix hints. Deterministic linter, not a detector.
我該用這個嗎
品質與安全性
B
根據工具定義與協定合規性的自動化分析。
上下文成本
~230Token(工具定義)
~343 B典型回應大小
極小的注意力影響(128k 上下文的 0.18%)
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": {
"slopscore": {
"url": "https://slopscore-nine.vercel.app/mcp"
}
}
}遠端端點
https://slopscore-nine.vercel.app/mcpstreamable-http它能做什麼
工具清單
工具(3)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢slop_check(text)
FREE (up to 5000 chars). Score a draft for AI-writing tells ("AI slop") and list each tell with its location and a fix hint. Use before publishing any text you generated.
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string"
}
},
"required": [
"text"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢slop_check_long(text)
PAID $0.002 USDC via x402 (Base). Same as slop_check for texts up to 200000 chars.
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string"
}
},
"required": [
"text"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢slop_patterns
FREE. List every AI-writing pattern DraftCheck detects, with a fix hint for each.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據
近期觀測
已驗證未記錄版本3 個工具