Add QueueSim's MCP server to Claude, Cursor or any MCP app. Describe your queue in plain words; Claude runs a real discrete event simulation and reads back the numbers. Free, no sign-up, no API key.
"I have 30 calls an hour, each takes 4 minutes, 3 agents — what's my wait?" Claude runs a discrete event simulation and reports wait time, queue length, utilization, and throughput.
Single Server, Coffee Shop, Grocery Checkout, Call Center. Run the defaults, or dial in your own numbers. Mirrors the scenarios in the QueueSim simulator.
Little's Law, utilization, Erlang-C, and the ways real queues (abandonment, priority, skills-based routing, breakdowns) break classical M/M/c assumptions.
Registered as com.queuesim/public on registry.modelcontextprotocol.io, the domain-verified MCP directory. Your MCP client can find it by name.
Every simulation response carries an explicit provenance line telling the model the numbers came from a real discrete-event run, not training-data recall. So the answer you read is the answer the engine produced.
recommend_staffing as a first-class tool"How many servers do I need to keep wait under 3 minutes?" is a different problem from "what's the wait at c=4?" QueueSim binary-searches the smallest staffing that meets your target in one call.
Settings → Connectors (or Custom Integrations). Add MCP server:
https://queuesim.com/mcp/v1No auth. Open a chat and try one of the prompts below.
Edit claude_desktop_config.json:
{
"mcpServers": {
"queuesim": {
"command": "npx",
"args": ["-y", "mcp-remote",
"https://queuesim.com/mcp/v1"]
}
}
}Uses the mcp-remote bridge. Restart Desktop.
Settings → Features → Model Context Protocol → Add Custom MCP. Use the same URL:
https://queuesim.com/mcp/v1Same install pattern works for Windsurf and any other MCP-speaking client.
Run a generic M/M/c queue. Inputs: arrival rate (λ), service rate per server (μ), server count (c), optional distributions. Returns per-hour metrics + summary.
Inverse of simulate_mmc. Give it λ, μ, and a target average wait — it binary-searches the smallest server count that meets the target. One call instead of five iterated by hand.
Run the same M/M/c through both closed-form Erlang-C and the DES engine. Side-by-side with deltas, as a sanity check on the engine. Where the two part ways on a real day.
Run your own 24-hour day: per-hour arrival rates and staffing, one service time. For a real Tuesday that doesn't look like any preset.
One shared line against a separate line per server, with the same staff and the same demand. Shows how much wait pooling saves.
Given an M/M/c config (and optionally an observed wait), returns a queueing-theory framed interpretation: where you sit on the utilization curve, what ρ means in plain language, and what M/M/c can't see.
List the four preset scenarios: Single Server, Coffee Shop, Grocery Checkout, Call Center.
Full detail for one scenario: background note, per-hour defaults, supported overrides.
Run a preset with optional overrides (servers, arrival rate, service time, days, distributions).
~500-word primer on M/M/c: Little's Law, utilization, why averages mislead, Erlang-C vs simulation.
Plain description of six real-world patterns classical M/M/c can't model — abandonment, priority tiers, overflow, skills-based routing, compound service, server outages.
Click a prompt to copy it.
simulate_mmc. Expect wait ~2 minutes, ρ ≈ 0.67.
recommend_staffing. Searches for the smallest c instead of trying counts by hand.
compare_analytical_vs_simulated. Closed-form vs DES side-by-side.
describe_scenario + simulate_scenario. Claude explains the peak staffing question.
simulate_scenario with an override. Trade-off lands in the numbers.
explain_queueing_theory.
explain_advanced_patterns. Explains priority + outages, points you at ChiAha for custom modeling.
Customers abandon lines. VIPs cut in. Skills-based routing, overflow groups, breaks, transfers and after-call work each break M/M/c's assumptions in a way that matters. The free MCP can describe these patterns. Running one against your numbers takes a custom discrete event model, and ChiAha builds those.