Graphistry MCP Server

Graphistry MCP server - GPU-accelerated graph visualization for MCP clients

Local serverstdioPython

What is the Graphistry MCP Server?

Graphistry MCP server - GPU-accelerated graph visualization for MCP clients

What you get

GPU-accelerated graph visualization and analytics for Large Language Models using Graphistry and MCP.

This project integrates Graphistry's powerful GPU-accelerated graph visualization platform with the Model Control Protocol (MCP), enabling advanced graph analytics capabilities for AI assistants and LLMs. It allows LLMs to visualize and analyze complex network data through a standardized, LLM-friendly interface.

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
visualize_graphVisualize a graph or hypergraph using Graphistry's GPU-accelerated renderer.
get_graph_idsList all stored graph IDs in the current session.
get_graph_infoGet metadata (node/edge counts, title, description) for a stored graph.
apply_layoutApply a standard layout (force_directed, radial, circle, grid) to a graph.
detect_patternsRun network analysis (centrality, community detection, path finding, anomaly detection).
encode_point_colorSet node color encoding by column (categorical or continuous).
encode_point_sizeSet node size encoding by column (categorical or continuous).
encode_point_iconSet node icon encoding by column (categorical, with icon mapping or binning).
encode_point_badgeSet node badge encoding by column (categorical, with icon mapping or binning).
apply_ring_categorical_layoutArrange nodes in rings by a categorical column (e.g., group/type).
apply_group_in_a_box_layoutArrange nodes in group-in-a-box layout (requires igraph).
apply_modularity_weighted_layoutArrange nodes by modularity-weighted layout (requires igraph).
apply_ring_continuous_layoutArrange nodes in rings by a continuous column (e.g., score).
apply_time_ring_layoutArrange nodes in rings by a datetime column (e.g., created_at).

How to install the Graphistry MCP Server

{
  "mcpServers": {
    "graphistry": {
      "command": "npx",
      "args": ["-y", "@silkspace/graphistry-mcp"],
      "env": {
        "GRAPHISTRY_USERNAME": "your-value",
        "GRAPHISTRY_PASSWORD": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
GRAPHISTRY_USERNAMEConfiguration value read at startup.Optional
GRAPHISTRY_PASSWORDConfiguration value read at startup.Optional

Example prompts to try

  • “Use Graphistry to visualize graph.”
  • “Use Graphistry to get graph ids.”
  • “Use Graphistry to get graph info.”

Frequently asked questions

Graphistry MCP server - GPU-accelerated graph visualization for MCP clients Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.