lm for Grok
io.github.houtini-ai/lm
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
client:Grok
transport:stdio
runtime:npm
Install lm in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"lm": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@houtini/lm"
],
"env": {
"HOUTINI_LM_ENDPOINT_URL": "<HOUTINI_LM_ENDPOINT_URL>",
"HOUTINI_LM_API_KEY": "<HOUTINI_LM_API_KEY>",
"HOUTINI_LM_MODEL": "<HOUTINI_LM_MODEL>",
"HOUTINI_LM_PROVIDER": "<HOUTINI_LM_PROVIDER>"
}
}
}
}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