AskHound
Find people asking for or seeking alternatives to a product, live from Stack Exchange and Bluesky.
我該用這個嗎
品質與安全性
發現項目(3)
- HIGH
- MEDIUM在 find_conversations 中
- INFO在 find_conversations 中
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": {
"askhound": {
"url": "https://askhound.haullabs.dev/api/mcp"
}
}
}遠端端點
https://askhound.haullabs.dev/api/mcpstreamable-http它能做什麼
工具清單
工具(4)
🟡find_conversations(query, days, limit, sources, context, ...)
Find recent public posts where people ask for a tool, an alternative, or help with a job, so you can decide whether an honest, disclosed reply would help them. Remote server covers Stack Exchange (incl. softwarerecs) and Bluesky; for Hacker News + GitHub run the local MCP: npx -y https://askhound.haullabs.dev/askhound.tgz mcp. Returns url, title, snippet, date, source and required attribution. Never auto-post replies.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Plain phrase, e.g. \"otter alternative\" or \"transcript export\""
},
"days": {
"type": "number",
"default": 30
},
"limit": {
"type": "number",
"default": 25
},
"sources": {
"type": "array",
"items": {
"enum": [
"se",
"bsky"
]
}
},
"context": {
"type": "array",
"items": {
"type": "string"
},
"description": "At least one must appear (kills noise), e.g. [\"meeting\",\"transcript\"]"
},
"exclude": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"query"
]
}🟢build_intent_queries(product, competitors, category, jobs)
Turn a product description into buying-intent search phrases (competitor alternatives, switching, export, pricing pain, recommendations).
輸入結構描述
{
"type": "object",
"properties": {
"product": {
"type": "string"
},
"competitors": {
"type": "array",
"items": {
"type": "string"
}
},
"category": {
"type": "string"
},
"jobs": {
"type": "array",
"items": {
"type": "string"
}
}
}
}🟢run_intent_pack(product, competitors, category, jobs, context, ...)
build_intent_queries + find_conversations for every phrase, merged and deduplicated, newest first.
輸入結構描述
{
"type": "object",
"properties": {
"product": {
"type": "string"
},
"competitors": {
"type": "array",
"items": {
"type": "string"
}
},
"category": {
"type": "string"
},
"jobs": {
"type": "array",
"items": {
"type": "string"
}
},
"context": {
"type": "array",
"items": {
"type": "string"
}
},
"days": {
"type": "number",
"default": 14
}
}
}🟢reply_policy
The honest-reply rules AskHound users agree to. Read before drafting any reply.
輸入結構描述
{
"type": "object",
"properties": {}
}社群
證據