Frequently Asked Questions about MCP Server

Q: What is MCP Server? A: MCP Server is a lightweight Python interface that exposes TigerGraph operations (queries, schema, vertices, edges, UDFs) as structured tools and URI-based resources for MCP agents.

Q: What is the purpose of MCP Server? A: The purpose of MCP Server is to act as a bridge between TigerGraph databases and AI agents, allowing AI models to access and interact with graph data.

Q: What are the key features of MCP Server? A: Key features include schema introspection, query execution, vertex & edge upsert, resource URIs, and UDF & algorithm listing.

Q: How do I install MCP Server? A: You can install MCP Server by cloning the repository, creating a virtual environment, installing dependencies, and configuring environment variables.

Q: What environment variables do I need to configure? A: You need to configure TG_HOST, TG_GRAPH, and TG_SECRET environment variables.

Q: Can MCP Server be used with Claude? A: Yes, MCP Server can be installed into the Claude Desktop client to allow Claude to invoke your TigerGraph tools directly.

Q: What is the license for MCP Server? A: MCP Server is licensed under the MIT License.

Q: How does MCP Server integrate with UBOS? A: MCP Server seamlessly integrates with the UBOS platform, a full-stack AI Agent Development Platform, allowing for easy deployment, management, and orchestration of AI agents that leverage graph data.

Q: What are the benefits of using UBOS with MCP Server? A: Benefits include accelerated development, simplified deployment, enhanced scalability, and improved collaboration on AI agent projects.

Q: Where can I find the source code for MCP Server? A: The source code is available on the GitHub repository: https://github.com/Muzain187/TG_MCP.