MCP server
Workloadtruth
Classifies GPU workloads as inference or training from telemetry alone via MCP tools.
Runs locally
- Pricing
- Open source
- Runs
- Locally
- Version
- 0.1.4
- Listing updated
- 3 months ago
About Workloadtruth
Workloadtruth is an open-source MCP server. It runs locally on your machine and is started by your AI client.
Install
Run in a terminal
claude mcp add workloadtruth -- uvx workloadtruth-cliAdd to claude_desktop_config.json
{
"mcpServers": {
"workloadtruth": {
"command": "uvx",
"args": [
"workloadtruth-cli"
]
}
}
}Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:
Add to ~/.cursor/mcp.json
{
"mcpServers": {
"workloadtruth": {
"command": "uvx",
"args": [
"workloadtruth-cli"
]
}
}
}Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:
Add to .vscode/mcp.json
{
"servers": {
"workloadtruth": {
"type": "stdio",
"command": "uvx",
"args": [
"workloadtruth-cli"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"workloadtruth": {
"command": "uvx",
"args": [
"workloadtruth-cli"
]
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"workloadtruth": {
"command": "uvx",
"args": [
"workloadtruth-cli"
]
}
}
}Using several servers? Build one config file with the MCP config generator.
Pricing
Open source
Workloadtruth FAQ
Is Workloadtruth free?
Yes. Workloadtruth is open source, so you can use and self-host it for free.
How do I add Workloadtruth to Claude Code?
Run this command in your terminal: claude mcp add workloadtruth -- uvx workloadtruth-cli
Where this comes from
- Description: from the official MCP Registry entry.
- Install steps: from the official MCP Registry entry.