agentcents for Grok
io.github.labham-llc/agentcents
Local LLM cost proxy: forecasts each call and recommends the cheapest model that clears the task.
client:Grok
transport:stdio
runtime:pypi
Install agentcents in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"agentcents": {
"type": "stdio",
"command": "uvx",
"args": [
"agentcents"
]
}
}
}Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs