Frequently Asked Questions about Ontology MCP Server

Q: What is the Ontology MCP Server? A: The Ontology MCP server is a tool that connects AI models like Claude to GraphDB’s SPARQL endpoint and Ollama models. It enables Claude to query and manipulate ontology data, and allows the utilization of various AI models.

Q: What are the main functionalities related to SPARQL? A: The main SPARQL-related functionalities include executing SPARQL queries (mcp_sparql_execute_query), executing SPARQL update queries (mcp_sparql_update), listing repositories (mcp_sparql_list_repositories), listing graphs (mcp_sparql_list_graphs), and retrieving resource information (mcp_sparql_get_resource_info).

Q: What are the main functionalities related to Ollama models? A: The main Ollama model-related functionalities include running models (mcp_ollama_run), showing model information (mcp_ollama_show), downloading models (mcp_ollama_pull), listing models (mcp_ollama_list), deleting models (mcp_ollama_rm), chat completion (mcp_ollama_chat_completion), and checking container status (mcp_ollama_status).

Q: What are the main functionalities related to OpenAI? A: The main OpenAI-related functionalities include chat completion (mcp_openai_chat), image generation (mcp_openai_image), text-to-speech conversion (mcp_openai_tts), speech-to-text conversion (mcp_openai_transcribe), and embedding generation (mcp_openai_embedding).

Q: What are the main functionalities related to Google Gemini? A: The main Google Gemini-related functionalities include text generation (mcp_gemini_generate_text), chat completion (mcp_gemini_chat_completion), and listing models (mcp_gemini_list_models).

Q: What HTTP request functionalities are available? A: The server supports executing HTTP requests (mcp_http_request) using various HTTP methods such as GET, POST, PUT, and DELETE, enabling communication with external APIs.

Q: How do I start using the Ontology MCP Server? A: To get started, clone the repository, set up the GraphDB Docker container, build and run the MCP server, import RDF data, and configure Claude Desktop with the necessary settings.

Q: Where can I find the Claude Desktop configuration file? A: The Claude Desktop configuration file can be found at the following locations:

• Windows: %AppData%Claudeclaude_desktop_config.json
• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

Q: What settings do I need to add to the Claude Desktop configuration file? A: You need to add the mcpServers configuration with the necessary command, arguments, environment variables (SPARQL_ENDPOINT, OPENAI_API_KEY, GEMINI_API_KEY), and ensure that the path to the built project directory is correct.

Q: Can I use the Ontology MCP Server with other AI models besides Claude? A: While the initial focus is on Claude, the architecture is designed to be extensible. Future development plans include supporting a wider range of AI models and knowledge graph databases.

Q: What is UBOS, and how does the Ontology MCP Server fit into the UBOS platform? A: UBOS is a Full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. The Ontology MCP server is a valuable asset within the UBOS ecosystem, enabling AI agents to access and leverage structured knowledge. UBOS provides the tools and infrastructure needed to orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems.