
πΈοΈ First NetworkX MCP server for graph analysis in AI conversations | Community & Enterprise
πΈοΈ First NetworkX MCP server for graph analysis in AI conversations | Community & Enterprise editions | Graph algorithms β’ Network analysis β’ MCP integration
Β·
A comprehensive Model Context Protocol (MCP) server providing advanced graph analysis capabilities using NetworkX.
The server follows a clean modular architecture:
βββ Core Layer # Basic graph operations and MCP server
βββ Handler Layer # Function organization and re-exports
βββ Advanced Layer # Specialized algorithms and features
βββ Supporting Layer # Monitoring, security, and infrastructureSee ARCHITECTURE.md for detailed architectural documentation.
git clone https://github.com/username/networkx-mcp-server.git
cd networkx-mcp-server
pip install -e .from networkx_mcp.server import create_graph, add_nodes, add_edges
# Create a graph
result = create_graph("my_graph", "undirected")
# Add nodes and edges
add_nodes("my_graph", ["A", "B", "C"])
add_edges("my_graph", [("A", "B"), ("B", "C")])# Start the MCP server
python -m networkx_mcp
# Or use the development script
./run_tests.shThe project maintains 80%+ test coverage with comprehensive test suites:
# Run all tests
pytest
# Run with coverage
pytest --cov=src/networkx_mcp --cov-report=html
# Run specific test categories
pytest tests/unit/ # Unit tests
pytest tests/integration/ # Integration tests
pytest tests/performance/ # Performance testsWe welcome contributions! Please see our Development Guide for:
# Install development dependencies
pip install -e ".[dev]"
# Install pre-commit hooks
pre-commit install
# Run the test suite
pytestThis project maintains high quality standards:
See pyproject.toml for complete dependency list.
# Build and run with Docker
docker build -t networkx-mcp-server .
docker run -p 8000:8000 networkx-mcp-server# Deploy to Kubernetes
kubectl apply -f k8s/See deployment documentation for production deployment guides.
The server is optimized for performance:
Security is a top priority:
Built-in observability features:
networkx-mcp-server/
βββ src/networkx_mcp/ # Main source code
β βββ core/ # Core graph operations
β βββ handlers/ # Function handlers
β βββ advanced/ # Advanced algorithms
β βββ monitoring/ # Monitoring and observability
β βββ security/ # Security features
βββ tests/ # Comprehensive test suite
βββ docs/ # Documentation
βββ scripts/ # Development and deployment scripts
βββ examples/ # Usage examplesThis project is licensed under the MIT License - see the LICENSE file for details.
Built with β€οΈ for the graph analysis community
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/networkx-mcp-server to learn what the "NetworkX MCP Server" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
docker run -p 8000:8000 networkx-mcp-serverThis server doesn't publish a machine-readable tool manifest, and it doesn't expose a public endpoint we could ask. Connect the server locally to see what it exposes.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/networkx-mcp-server)Nothing comparable is listed yet.
v1.0.0π NetworkX MCP Server v1.0.0 - Production ReleaseRelease notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "networkx-mcp-server" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.