Claude Code
Run once in your terminal:
claude mcp add line-solver -- line-mcp
Check it with claude mcp list.
Model Context Protocol
Connect LINE to an AI assistant, describe a system in plain language, and get queue lengths, utilization, response times, and throughput.
This installs the solver and the line-mcp server.
pip install line-solver
Choose the client you use.
Run once in your terminal:
claude mcp add line-solver -- line-mcp
Check it with claude mcp list.
Add this to claude_desktop_config.json, then restart Claude:
{
"mcpServers": {
"line-solver": {
"command": "line-mcp"
}
}
}
which line-mcp and use the returned absolute path in your client configuration.
The assistant chooses the LINE tool and solver, then explains the result.
“Analyze an M/M/1 queue with arrival rate 2 and service rate 5.” Single queue
“Eight jobs circulate through stations with demands 0.5 and 0.3. Find the bottleneck.” Queueing network
“Sweep arrival rate from 0.5 to 2.5 and show how response time changes.” Parameter sweep
Create open, closed, mixed, multiclass, fork/join, and layered models.
Get averages, distributions, percentiles, transient results, or simulation traces.
Sweep parameters, compare solvers, inspect examples, and visualize topology.
Work with LINE JSON, JMT, PNML, LQNX, MATLAB, pickle, and Python.
You usually do not need to call tools yourself. These groups are useful when you want to guide the assistant.
analyze_queue, analyze_network, sweep_parameterbuild_network, build_topology, build_from_gallerysolve_model_file, find_solver, compare_solvers, convert_modellist_gallery, list_examples, list_solvers, check_installNeed every argument, solver, and output format? Open the complete MCP guide (PDF).