Connect Cloud World Model and your agent gets 10 tools, among them scenario.get, scenario.list, simulation.create. It answers at https://www.cloudworldmodel.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 29 September 2026; the last check, on 14 November 2026, succeeded.
Simulate cloud architectures before provisioning. 9 free demo tools; an API key unlocks all 62.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
scenario.get | Requires scenarioId returned by scenario.list (also available as id). Returns the complete selected graph, presets, assumptions and phase details. Next tool is simulation.create with scenarioId or the hydrated resources/connections. No API Inputs: scenarioId |
scenario.list | No prerequisites. Returns paginated scenarios cards with scenarioId (alias of id), name, summary and available provider/category/difficulty. Pass scenarioId to scenario.get. Filters precede stable ID paging: limit default 8, maximum 20; pas Inputs: limit, cursor, detailed, provider, category, difficulty |
simulation.create | Create from scenarioId (scenario.list → scenario.get), or resources/connections for a custom graph. Returns id for simulation.step. Never blindly retry a timeout: creation may have succeeded. No API key required; demo limits apply. Read res Inputs: costAssumptions, name, appWeight, description, scenarioId, scenarioOverrides |
simulation.delete | The likely next tool is simulation.create to use the freed slot. Prerequisite: a simulationId from simulation.create, or an active simulation in the preserved MCP session. No API key required; demo limits apply. Read resource cwm://guides/p Inputs: simulationId |
simulation.from_input | Key/content/target;cloud terraform-plan:no host;DaemonSet:placement.workers,placement.podSlotsPerWorker;GPU;simulation.step Read resource cwm://guides/public/simulation.from_input Inputs: format, content, filename, files, environment, activeProfiles |
simulation.inject_failure | Requires simulationId and resourceId from simulation.create. Injects a bounded resource failure; returns updated state. Next tool is simulation.step, then simulation.recover_resource and simulation.metrics to confirm authoritative health. N Inputs: simulationId, resourceName, resourceId, nodePoolId, nodePoolName, type |
simulation.inject_traffic | Requires simulationId from simulation.create and target traffic RPS. Returns applied traffic settings. Next tool is simulation.step, then simulation.metrics to read observed latency; do not assume its direction. No API key required; demo li Inputs: simulationId, targetRps, deltaPercent, ramp, random |
simulation.metrics | Requires simulationId from simulation.create (demo optional). Returns latest/history; full=evidence. CWM_RAMP_GAP_NOT_ERRORS="true": owned AWS lean/2-app typical-v1 (500-RPS diagnostic) returns rampAveragingShortfallPct=100*(1-throughput/of Inputs: simulationId, responseMode |
simulation.recover_resource | Requires simulationId and resourceId from simulation.create. Requests reversible resource recovery; success does not prove healthy. Next tool is simulation.step, then simulation.metrics to inspect resource health. No API key required; demo Inputs: simulationId, resourceName, resourceId |
simulation.step | Requires simulationId from simulation.create (optional in demo). Returns completedSteps/currentStep; next tool is simulation.metrics. Retry same operationId/inputs. CWM_RAMP_GAP_NOT_ERRORS="true": owned AWS lean/2-app typical-v1 (500-RPS di Inputs: operationId, expectedCheckpoint, simulationId, steps, traffic, responseMode |
Every block below points at https://www.cloudworldmodel.ai/mcp. Pick your client and copy.
claude mcp add --transport http cloud-world-model https://www.cloudworldmodel.ai/mcp
{
"mcpServers": {
"cloud-world-model": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://www.cloudworldmodel.ai/mcp"]
}
}
}{
"mcpServers": {
"cloud-world-model": {
"url": "https://www.cloudworldmodel.ai/mcp"
}
}
}{
"servers": {
"cloud-world-model": {
"type": "http",
"url": "https://www.cloudworldmodel.ai/mcp"
}
}
}{
"context_servers": {
"cloud-world-model": {
"url": "https://www.cloudworldmodel.ai/mcp"
}
}
}{
"mcpServers": {
"cloud-world-model": {
"serverUrl": "https://www.cloudworldmodel.ai/mcp"
}
}
}{
"mcpServers": {
"cloud-world-model": {
"url": "https://www.cloudworldmodel.ai/mcp"
}
}
}name: Cloud World Model
version: 0.0.1
schema: v1
mcpServers:
- name: Cloud World Model
type: streamable-http
url: https://www.cloudworldmodel.ai/mcp{
"mcpServers": {
"cloud-world-model": {
"httpUrl": "https://www.cloudworldmodel.ai/mcp"
}
}
}{
"mcpServers": {
"cloud-world-model": {
"type": "http",
"url": "https://www.cloudworldmodel.ai/mcp"
}
}
}{
"mcpServers": {
"cloud-world-model": {
"url": "https://www.cloudworldmodel.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fwww.cloudworldmodel.ai%2Fmcp&type=streamable_http&id=cloud-world-model&name=Cloud%20World%20Model
It answered our last check on 14 November 2026 in 187 ms. Over 4 checks since 29 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by cloudworldmodel.ai and served from www.cloudworldmodel.ai, the vendor's own domain: https://www.cloudworldmodel.ai/mcp.
10, as returned by the server's own tools/list on 17 November 2026: scenario.get, scenario.list, simulation.create, simulation.delete, simulation.from_input, simulation.inject_failure, simulation.inject_traffic, simulation.metrics, and 2 more.
It answered our last check on 14 November 2026 in 187 ms. Over 4 checks since 29 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://www.cloudworldmodel.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.cloudworldmodel. Endpoint host: www.cloudworldmodel.ai. ARD identifier: urn:air:ai.cloudworldmodel:mcp:cloud-world-model.
First indexed 29 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.