tablebridge-mcp

Michael-WhiteCapData/tablebridge-mcp
★ 1 stars Python AI/LLM Updated today
MCP server: query a folder of CSV/Parquet/JSON files with SQL (DuckDB), read-only & sandboxed. pip install tablebridge
View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "tablebridge-mcp": {
      "command": "uvx",
      "args": [
        "tablebridge-mcp"
      ]
    }
  }
}

Or install with pip: pip install tablebridge-mcp

README Excerpt

<!-- mcp-name: io.github.Michael-WhiteCapData/tablebridge-mcp --> **Turn a folder of CSV / Parquet / JSON files into one SQL-queryable source for your AI agent.** Small businesses don't have a data warehouse — they have a folder full of exports: `customers.csv`, last month's `orders.xlsx`, a `regions.json` someone emailed over. `tablebridge` is an [MCP](https://modelcontextprotocol.io/) server that points [DuckDB](https://duckdb.org/) at that folder, exposes **each file as a SQL table**, and let

Tools (9)

TABLEBRIDGE_DATA_DIRTABLEBRIDGE_MAX_ROWSTABLEBRIDGE_RECURSIVEdescribelist_sourcespreviewqueryrefreshserver_info

Topics

claudecsvdata-integrationduckdbmcpmodel-context-protocolpythonsql