FirstPass Memo listing check
Red-flag check for business-for-sale listings: payback, asking multiple, flags, seller questions.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
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": {
"listing-check": {
"url": "https://firstpassmemo.com/mcp"
}
}
}遠端端點
https://firstpassmemo.com/mcpstreamable-http它能做什麼
工具清單
工具（2）
🟢check_listing(listing_text, asking_price, monthly_profit, monthly_revenue, age_months, ...)
Runs FirstPass Memo's 33 published red-flag rules on a small online-business listing (SaaS, content site, ecommerce, Amazon FBA, newsletter, app; roughly $10k-$150k) from Flippa, Empire Flippers, Acquire.com or any broker. Pass the listing text the user provides and/or the key numbers. Returns payback in months, the asking multiple vs comparable listings, every flag that fired (severity, why it matters, link to the rule) and questions to ask the seller. Screening only: not advice, a valuation or verification. Does not fetch URLs.
輸入結構描述
{
"type": "object",
"properties": {
"listing_text": {
"type": "string",
"description": "Listing text pasted by the user (asking price, profit, revenue, age, traffic, churn, etc.). Max 20,000 characters."
},
"asking_price": {
"type": "number",
"description": "Asking price in USD. Overrides any price found in the text."
},
"monthly_profit": {
"type": "number",
"description": "Average monthly net profit in USD."
},
"monthly_revenue": {
"type": "number",
"description": "Average monthly revenue in USD."
},
"age_months": {
"type": "number",
"description": "Months the business has been making money."
},
"category": {
"type": "string",
"enum": [
"SaaS or software",
"Subscription or newsletter",
"Content site (display ads)",
"Affiliate site",
"Amazon FBA or FBM",
"Ecommerce (not Amazon)",
"Dropshipping",
"YouTube channel",
"Digital product",
"Service or agency",
"Other"
],
"description": "Business type."
},
"traffic_sources": {
"type": "string",
"description": "Traffic mix, e.g. 'Organic search 70%, Direct 20%, Social 10%'."
}
}
}🟢list_rules
Returns the 33 published rules the checker uses (code, title, group, severity, when it fires, explainer URL).
輸入結構描述
{
"type": "object",
"properties": {}
}社群
證據