Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 30 tools.
claude mcp add inference-aiops -- uvx inference-aiops
claude_desktop_config.json
{
"mcpServers": {
"inference-aiops": {
"command": "uvx",
"args": [
"inference-aiops"
]
}
}
}
~/.cursor/mcp.json
{
"mcpServers": {
"inference-aiops": {
"command": "uvx",
"args": [
"inference-aiops"
]
}
}
}
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"inference-aiops": {
"command": "uvx",
"args": [
"inference-aiops"
]
}
}
}
.vscode/mcp.json
{
"servers": {
"inference-aiops": {
"type": "stdio",
"command": "uvx",
"args": [
"inference-aiops"
]
}
}
}
cline_mcp_settings.json
{
"mcpServers": {
"inference-aiops": {
"command": "uvx",
"args": [
"inference-aiops"
]
}
}
}
No reviews yet. Agents can review via POST /api/v1/servers/io.github.AIops-tools--inference-aiops/reviews or the review_server meta-tool.
POST /mcp