Tablebridge MCP Server

Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.

Local serverstdio

What is the Tablebridge MCP server?

Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only. Exposed over MCP by the tablebridge mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

It's read-only and sandboxed: files are loaded into an in-memory database, the data directory is the only thing it can see, and queries are validated so an agent can't write, escape to other paths, or call raw file functions.

  • 🔗 One source over many files. JOIN orders.csv to customers.csv to regions.json in a single query — no ETL, no database to stand up
  • 🦆 DuckDB-powered. Fast analytical SQL over CSV, TSV, Parquet, JSON/NDJSON
  • 🔒 Safe by design. Files are materialized into memory; queries are validated read-only; raw file-access functions and out-of-sandbox paths are rejected
  • 🤖 Agent-friendly. list_sources → describe → query is a natural flow the agent can follow on its own
  • 🪶 Two dependencies (mcp, duckdb), fully typed and tested

Adding it to your client

tablebridge on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Its toolset

Everything the assistant can do here goes through one of these:

  • list_sources — List the tables (one per data file) with column counts — start here
  • describe — A table's columns and types
  • preview — First N rows of a table
  • query — Run read-only SQL (DuckDB dialect) across the tables, JOINs included
  • refresh — Re-scan the data directory for added/changed files
  • server_info — Effective config (data dir, row cap, supported formats)

Configuration

You will need one environment variable: TABLEBRIDGE_DATA_DIR. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the tablebridge mcp server does with a few real requests.

When to reach for it

Plenty of database access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Tablebridge's toolset — list_sources, describe, preview and 3 more — is a fair guide to whether it matches your workflow. It is maintained by Michael-WhiteCapData; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
list_sourcesList the tables (one per data file) with column counts — start here
describeA table's columns and types
previewFirst N rows of a table
queryRun read-only SQL (DuckDB dialect) across the tables, JOINs included
refreshRe-scan the data directory for added/changed files
server_infoEffective config (data dir, row cap, supported formats)

How to install the Tablebridge MCP server

{
  "mcpServers": {
    "tablebridge": {
      "command": "uvx",
      "args": ["tablebridge"],
      "env": { "TABLEBRIDGE_DATA_DIR": "/path/to/your/data" }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
TABLEBRIDGE_DATA_DIRFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Tablebridge to list sources.
  • Use Tablebridge to describe.
  • Use Tablebridge to preview.

Frequently asked questions

It connects Tablebridge to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (list_sources, describe, preview, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Tablebridge directly.