Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
graphistry-mcp
GPU-accelerated graph visualization and analytics for Large Language Models using Graphistry and MCP
11stars
3forks
Python
Quality signals
StaleNo testsNo CIThin docsNo licenseNew
AI summary
Auto-generated overview of what this skill does and when to reach for it.
GPU-accelerated graph visualization and analytics for LLMs via Graphistry and MCP.
Use this when
- Debugging complex network data with LLMs
- Exploring relationships in large datasets interactively
- Generating visual graphs from code or natural language prompts
- Analyzing social networks, knowledge graphs, or dependency graphs
- Detecting anomalies or patterns in connected data
Don't use when
- Need static image exports without GPU acceleration
- Working with non-graph data (e.g., tabular spreadsheets)
- Requiring offline-first or air-gapped environments
Capabilities
- Visualize graphs/hypergraphs with GPU acceleration
- Apply layouts (force-directed, radial, tree, etc.)
- Run network analysis (centrality, community detection, pathfinding)
- Encode nodes by color/size/icon/badge using data columns
- Store and retrieve graph metadata (node/edge counts, titles)
- Support Pandas, NetworkX, and edge-list data formats
InstallMCPInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest graphistry/graphistry-mcpAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/graphistry-mcp curl -fsSL https://raw.githubusercontent.com/graphistry/graphistry-mcp/main/README.md -o ~/.claude/skills/graphistry-mcp/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
graphistry-mcp — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt