Frequently Asked Questions about FindMCP

Q: What is FindMCP? A: FindMCP is a specialized Model Context Protocol (MCP) server that provides directory information for MCP services, primarily those hosted on Smithery.ai. It allows AI models to discover and utilize external tools and resources.

Q: What is MCP? A: MCP stands for Model Context Protocol. It’s an open standard that defines how applications provide context to Large Language Models (LLMs), enabling them to access external data and tools.

Q: How does FindMCP work with Cursor? A: FindMCP integrates with the Cursor editor by being added as an MCP server in Cursor’s settings. Once configured, AI models within Cursor can be instructed to use FindMCP to access Smithery.ai’s MCP services.

Q: What is Smithery.ai? A: Smithery.ai is a platform that hosts a variety of AI tools and services. FindMCP provides a directory to these services, making it easier for AI models to find and utilize them.

Q: How do I install FindMCP? A: You can install FindMCP locally using npm install. The official documentation provides detailed instructions for both local installation and deployment on Smithery.ai.

Q: How do I tell Cursor to use FindMCP? A: You can instruct the LLM within Cursor to use FindMCP by explicitly mentioning the smithery_search tool or using the @https://smithery.ai/ syntax in your prompts.

Q: What do I do if I get a “Failed to create client” error? A: This error often indicates an incorrect path configuration. Verify the path to the FindMCP execution script in Cursor’s settings and ensure that it’s properly escaped.

Q: What do I do if the LLM doesn’t use the MCP tool? A: Make sure the MCP server is successfully connected in Cursor’s settings. Use clear and explicit instructions mentioning the tool’s name. Try restarting the conversation or checking the Cursor console for error messages.

Q: Can I use FindMCP with platforms other than Cursor? A: Yes, FindMCP can be used with any MCP-compliant client. However, the documentation specifically focuses on Cursor integration.

Q: Where can I find more information about MCP? A: You can find more information about MCP at https://modelcontextprotocol.io/.