token compressor for Grok
io.github.base76-research-lab/token-compressor
Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
client:Grok
transport:stdio
runtime:pypi
Install token compressor in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"token-compressor": {
"type": "stdio",
"command": "uvx",
"args": [
"token-compressor-mcp"
]
}
}
}
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