StruXure NorCal Knowledge Base
Public remote MCP server for StruXure NorCal pergola services and FAQs.
我該用這個嗎
品質與安全性
A
根據工具定義與協定合規性的自動化分析。
上下文成本
~215Token（工具定義）
~731 B典型回應大小
極小的注意力影響（128k 上下文的 0.17%）
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": {
"struxure-knowledge-base": {
"url": "https://walnbot.struxurenorcal.com/mcp/struxure-knowledge-base"
}
}
}遠端端點
https://walnbot.struxurenorcal.com/mcp/struxure-knowledge-basestreamable-http它能做什麼
工具清單
工具（2）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢services(query, topK)
Find service offerings relevant to a natural-language query. Returns the closest matches, not a complete list — use `list_services` for the complete catalogue.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"description": "What the user wants — describe the service they're looking for.",
"type": "string"
},
"topK": {
"description": "Maximum number of results to return (1–20).",
"type": "integer",
"default": 8
}
},
"required": [
"query"
]
}⚪faq(query, topK)
Answer a question from this knowledge base's FAQ content. Returns the closest-matching FAQ passages, not extracted answers — for a customer reporting that something is broken, `troubleshoot` returns the resolution itself.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"description": "The question to answer from the FAQ.",
"type": "string"
},
"topK": {
"description": "Maximum number of results to return (1–20).",
"type": "integer",
"default": 8
}
},
"required": [
"query"
]
}社群
證據
近期觀測
已驗證未記錄版本2 個工具
已驗證未記錄版本2 個工具