Frequently Asked Questions about Graphistry MCP Server

Q: What is Graphistry MCP Server? A: Graphistry MCP Server integrates Graphistry’s GPU-accelerated graph visualization with the Model Control Protocol (MCP), allowing Large Language Models (LLMs) to perform advanced graph analytics.

Q: Why would I use Graphistry MCP Server? A: It enables LLMs to visualize and analyze complex network data, discover hidden patterns, and make more informed decisions. This is useful for cybersecurity, fraud detection, social network analysis, and more.

Q: Do I need a Graphistry account to use this? A: Yes, a free Graphistry account is required to use the visualization features. Sign up at hub.graphistry.com.

Q: What data formats are supported? A: The server supports various data formats including Pandas DataFrames, NetworkX graphs, and edge lists.

Q: What is the Model Control Protocol (MCP)? A: MCP is an open protocol that standardizes how applications provide context to LLMs, enabling AI models to access and interact with external data sources and tools.

Q: How do I install Graphistry MCP Server? A: Clone the repository, set up a virtual environment, install dependencies using pip, and configure your Graphistry credentials.

Q: How do I configure my Graphistry credentials? A: Set your GRAPHISTRY_USERNAME and GRAPHISTRY_PASSWORD as environment variables or in a .env file.

Q: What is the .mcp.json file for? A: The .mcp.json file configures the MCP server, setting paths, credentials, and communication modes (HTTP or stdio).

Q: How do I start the server? A: Activate your virtual environment and use the run_graphistry_mcp.py script or the start-graphistry-mcp.sh script.

Q: How do I add the server to Cursor or other LLM tools? A: Add the MCP server configuration to your LLM’s configuration file (e.g., .cursor/mcp.json), ensuring the virtual environment is used.

Q: What MCP tools are available? A: Available tools include visualize_graph, get_graph_ids, get_graph_info, apply_layout, detect_patterns, and various encoding and layout tools.

Q: Can I use this with UBOS? A: Yes, Graphistry MCP Server integrates seamlessly with UBOS, enhancing AI agent capabilities with graph visualization and analytics.

Q: Where can I find more information? A: Visit the Graphistry website at https://ubos.tech for detailed documentation, tutorials, and community support.