tablebridge mcp for Grok
io.github.michael-whitecapdata/tablebridge-mcp
Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.
client:Grok
transport:stdio
runtime:pypi
Install tablebridge mcp in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"tablebridge-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"tablebridge"
],
"env": {
"TABLEBRIDGE_DATA_DIR": "<TABLEBRIDGE_DATA_DIR>",
"TABLEBRIDGE_MAX_ROWS": "<TABLEBRIDGE_MAX_ROWS>",
"TABLEBRIDGE_RECURSIVE": "<TABLEBRIDGE_RECURSIVE>"
}
}
}
}
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