Add Nanobot Customer Service
@yt0912iii
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。
Overview
What is Add Nanobot Customer Service?
Add Nanobot Customer Service is a Model Context Protocol (MCP) server built with Python and FastMCP. It transforms local knowledge base documents (RAG system) into standardized AI tools that can be called directly by AI clients such as Cursor and Claude Desktop, enabling accurate retrieval of platform operation information.
How to use Add Nanobot Customer Service?
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.
Key features of Add Nanobot Customer Service
- 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
Use cases of Add Nanobot Customer Service
- AI assistants answering platform operation and feature questions
- Automated customer service responses based on curated knowledge base
- Reducing hallucinated answers when handling user inquiries about platform rules
- Enabling AI clients to retrieve accurate documentation without manual lookup
FAQ from Add Nanobot Customer Service
What does the search_customer_service_docs tool do?
It searches the knowledge base for platform usage information, frequently asked questions, and customer service documents. AI must call this tool when users ask about platform operations or visitor guidelines.
How is Add Nanobot Customer Service configured?
Add the JSON configuration shown in the README to your AI client’s mcpServers section, specifying the path to mcp_server.py and a Python interpreter.
Does Add Nanobot Customer Service prevent AI hallucinations?
Yes, it includes strict anti-hallucination guardrails. If no matching document is found, the tool will honestly report that no information is available rather than guessing.
What are the runtime dependencies?
The server requires Python and the FastMCP library, as it is built on the FastMCP architecture.
Which AI clients are supported?
The server is designed for MCP-compatible clients such as Cursor and Claude Desktop.
