Frequently Asked Questions (FAQ) about the Simple MCP Tool Server

Q: What is the Simple MCP Tool Server? A: The Simple MCP Tool Server is a Python-based server that exposes a website fetching tool and documentation search capabilities using the Model Context Protocol (MCP). It allows AI agents to access and interact with external data sources and tools.

Q: What is MCP (Model Context Protocol)? A: MCP is an open protocol that standardizes how applications provide context to LLMs (Large Language Models). It enables AI models to access and utilize up-to-date information, perform actions through external tools, and make more informed decisions.

Q: What are the key features of the Simple MCP Tool Server? A: The key features include a remote HTTP fetcher (fetch), semantic search across SDK documentation (search_docs), full local file retrieval (get_content), a simple command-line interface (CLI), and SSE transport for real-time communication.

Q: What are some use cases for the Simple MCP Tool Server? A: Use cases include web scraping and data collection, knowledge management and retrieval, content creation and summarization, code understanding and debugging, and real-time customer support.

Q: How do I install the Simple MCP Tool Server? A: You can install the server by creating a virtual environment, activating it, and then installing the required dependencies using pip install -r requirements.txt.

Q: How do I start the Simple MCP Tool Server? A: You can start the server using the default port (7000) with python -m mcp_simple_tool start or specify a custom port using python -m mcp_simple_tool start --port 8000.

Q: What is the fetch tool used for? A: The fetch tool allows AI agents to retrieve the HTML content of any website by providing its URL. This is essential for web scraping, data collection, and content analysis.

Q: What is the search_docs tool used for? A: The search_docs tool enables AI agents to perform semantic searches across the SDK documentation, retrieving the top-k excerpts that match a given query. This is crucial for knowledge retrieval, code understanding, and debugging.

Q: What is the get_content tool used for? A: The get_content tool allows AI agents to retrieve the full content of any file identified by the search_docs tool. This is useful for accessing complete documentation, code samples, and other relevant resources.

Q: How does the Simple MCP Tool Server integrate with Cursor? A: The server seamlessly integrates with the Cursor IDE by creating a .cursor/mcp.json file with the server configuration and mentioning the server in your prompts when using Cursor.

Q: Can I customize the Simple MCP Tool Server? A: Yes, the server is written in Python, making it easy to customize and extend for your specific needs. You can modify the existing tools or add new ones.

Q: What is UBOS and how does the Simple MCP Tool Server fit in? A: UBOS is a full-stack AI agent development platform. The Simple MCP Tool Server is a component that can be used with UBOS to provide context and access to external data sources for AI agents. UBOS offers tools for AI agent orchestration, enterprise data integration, custom AI agent development, and multi-agent systems.

Q: Where can I find the SDK documentation for the Simple MCP Tool Server? A: The MCP Python SDK documentation is located in the docs/ directory. It covers core concepts, running MCP servers in different modes, examples, and advanced usage.