Add Nanobot Customer Service
About
一個基於 Model Context Protocol (MCP) 的智慧客服 RAG 伺服器。本工具允許 AI 客戶端（如 Cursor、Claude Desktop）透過標準化 Tool 呼叫直接檢索平台的操作說明、常見問題與遊客須知知識庫。具備嚴格的防瞎掰機制，查無資料時誠實告知，確保 AI 客服回答的百分之百準確性。
Details
- Author
- yt0912iii
- Downloads
- 250
- Categories
- Search
Jump to
- Provides a single tool: search_customer_service_docs
- Queries platform usage info, FAQs, and customer service documentation
- Built-in anti-hallucination guardrails prevent unsupported guesses
- Returns honest “no results” when nothing is found
- Designed for integration with Cursor and Claude Desktop
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Add Nanobot Customer ServiceCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Add the provided JSON configuration snippet to your AI client’s configuration file, adjusting the Python and script absolute paths as needed. The server runs the mcp_server.py script and exposes a search_customer_service_docs tool.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"add nanobot customer service": {
"nanobot-customer-service": {
"command": "python",
"args": [
"mcp_server.py"
],
"env": {
"PYTHONUNBUFFERED": "1"
}
}
}
}
}McpServers
{
"nanobot-customer-service": {
"command": "python",
"args": [
"mcp_server.py"
],
"env": {
"PYTHONUNBUFFERED": "1"
}
}
}🧩 Nanobot Customer Service - MCP Server (Python/FastMCP)
這是一個專為企業與開發者設計的智慧客服 Model Context Protocol (MCP) 伺服器，基於 Python 的 FastMCP 架構開發。它能將本地的知識庫文檔（RAG 系統）無縫轉化為標準化的 AI 工具（Tools），讓 Cursor、Claude Desktop 等 AI 客戶端能直接呼叫並檢索最正確的平台運作資訊。 ---🛠️ 內含工具宣告 (Tools API)
1. search_customer_service_docs
功能描述：查詢平台使用資訊、遊客常見問題與客服知識庫文檔。當使用者詢問關於平台操作、功能說明或遊客須知時，AI 必須主動呼叫此工具獲取正確資訊。
輸入參數：
query (string, required): 想要查詢的關鍵字或問題描述。
設計特點：內建嚴格的「防瞎掰機制（Anti-Hallucination Guardrails）」，查無資料時將誠實告知，絕不進行無根據的猜測，確保自動化客服的回答精準度高達 100%。
---
🚀 伺服器配置指南 (Server Config)
想要在你的 AI 環境中啟用這個技能，請將以下 JSON 片段加入到你的客戶端設定檔中（請根據你的操作系統調整 Python 與腳本的絕對路徑）： ```json { "mcpServers": { "nanobot-customer-service": { "command": "python", "args": [ "mcp_server.py" ], "env": { "PYTHONUNBUFFERED": "1" } } } }Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
