StormForge MCP server
2 minute read
The StormForge CLI includes an MCP server for connecting AI agents to StormForge.
This guide covers configuration and basic usage, using Claude as an example.
Prerequisites
Make sure the StormForge CLI is installed and you are logged in:
stormforge login
Configure your AI agent
This example uses Claude, but the configuration pattern applies to other MCP-compatible agents such as ChatGPT and Gemini.
Add the following to your agent’s MCP configuration. For Claude, that can be ~/.claude.json:
{
"mcpServers": {
"stormforge": {
"command": "stormforge",
"args": ["mcp"]
}
}
}
If you installed the StormForge CLI in a custom location, you may need to provide an absolute path to the stormforge binary.
Claude Code
If you are using Claude Code, you can add the StormForge MCP server directly from the command line:
claude mcp add stormforge -- stormforge mcp
Example usage
Once connected, you can ask your agent questions about your workloads.
Example prompt:
What are the top 3 most overprovisioned workloads across my clusters?
Example response:
The top 3 are:
┌──────┬──────────────┬───────────────┬───────────┬─────────────────┐
│ Rank │ Workload │ Namespace │ Cluster │ Monthly Savings │
├──────┼──────────────┼───────────────┼───────────┼─────────────────┤
│ 1 │ <workload-1> │ <namespace-1> │ <cluster> │ $38.08 │
├──────┼──────────────┼───────────────┼───────────┼─────────────────┤
│ 2 │ <workload-2> │ <namespace-2> │ <cluster> │ $21.98 │
├──────┼──────────────┼───────────────┼───────────┼─────────────────┤
│ 3 │ <workload-3> │ <namespace-2> │ <cluster> │ $16.92 │
└──────┴──────────────┴───────────────┴───────────┴─────────────────┘
All three are on <cluster>. Notable details:
- <workload-1>: CPU can be cut from 1000m → 25m (97% reduction)
- <workload-2>: Memory can be cut from 1Gi → 32Mi (97% reduction)
- <workload-3>: Both CPU (1000m → 224m) and memory (1Gi → 364Mi) are significantly oversized
Your agent can use the following StormForge MCP tools:
list_clusterslist_namespaceslist_workloadslist_workloads_minimallist_recommendations