Enterprise DNA
M MCP Servers Developer low

Bright-L01/networkx-mcp-server

by Various

πŸ•ΈοΈ First NetworkX MCP server for graph analysis in AI conversations | Community & Enterprise editions | Graph algorithms β€’ Network analysis β€’ MCP integration

B

MCP

Bright-L01/networkx-mcp-server

Added 1 June 2026

#ai-tools #algorithms #community-detection #enterprise #first-of-kind #graph-algorithms #graph-analysis #mcp

Overview

An MCP server that exposes NetworkX graph algorithms for use within AI conversations. It implements the Model Context Protocol to let AI assistants run graph analysis tasks directly. Community and enterprise editions are available for different deployment needs.

Best for

Best for
Developers building AI assistants that need to perform graph analysis

Use cases

  • Analyze network graphs via AI chat interfaces
  • Run shortest path or centrality algorithms in conversations
  • Explore graph structures using natural language prompts

Notes

An MCP server that exposes NetworkX graph algorithms for use within AI conversations. It implements the Model Context Protocol to let AI assistants run graph analysis tasks directly. Community and enterprise editions are available for different deployment needs.

16 stars on GitHub. Last updated 2026-06-01. Licensed MIT.

Use cases

  • Analyze network graphs via AI chat interfaces
  • Run shortest path or centrality algorithms in conversations
  • Explore graph structures using natural language prompts

Pros

  • Integrates NetworkX with the MCP standard for AI tool use
  • Open-source community edition lowers entry barrier
  • Python-based, easy to set up and extend

Cons

  • Low GitHub popularity (16 stars) indicates early adoption
  • Requires an MCP-compatible AI client to be useful
  • Documentation and community support may be limited

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Integrates NetworkX with the MCP standard for AI tool use
  • Open-source community edition lowers entry barrier
  • Python-based, easy to set up and extend

Cons

  • Low GitHub popularity (16 stars) indicates early adoption
  • Requires an MCP-compatible AI client to be useful
  • Documentation and community support may be limited