tablebridge
About
Query a folder of CSV / Parquet / JSON files with SQL via DuckDB — read-only and sandboxed; scattered files become one queryable source.
Details
- Author
- michael-whitecapdata
- Categories
- Database, Other, File Management
Jump to
Setup
Install tablebridge in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/michael-whitecapdata/tablebridge-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
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'sorders.xlsx, aregions.jsonsomeone emailed over.tablebridgeis anMCPserver that pointsDuckDBat that folder, exposeseach file as a SQL table, and lets your agent runread-only SQL — including JOINs across files— to answer questions over all of them at once. Scattered spreadsheets become one queryable source of truth.
It'sread-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.JOINorders.csvtocustomers.csvtoregions.jsonin 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→queryis a natural flow the agent can follow on its own.
- 🪶Two dependencies(mcp,duckdb), fully typed and tested.
uvx tablebridge # run directly # or pip install tablebridge # then run: tablebridge
TABLEBRIDGE_DATA_DIR=/path/to/your/data claude mcp add tablebridge -- uvx tablebridge
{ "mcpServers": { "tablebridge": { "command": "uvx", "args": ["tablebridge"], "env": { "TABLEBRIDGE_DATA_DIR": "/path/to/your/data" } } } }
docker build -t tablebridge . docker run --rm -i -v /path/to/your/data:/data:ro tablebridge
With a folder containingcustomers.csv,orders.csv, andregions.json:
You:Who are my top 3 customers by total spend, and what region are they in?
Agent:(callslist_sources, thenquery)
SELECT c.name, r.region, SUM(o.total) AS spend FROM customers c JOIN orders o ON o.customer_id = c.id JOIN regions r ON r.customer_id = c.id GROUP BY c.name, r.region ORDER BY spend DESC LIMIT 3;
Supported formats:.csv,.tsv,.parquet,.json,.ndjson.
- SandboxedtoTABLEBRIDGE_DATA_DIR— only files under it are loaded.
- Materializedinto an in-memory DuckDB, then external filesystem access is disabled — queries can't reach other paths.
- Validated SQL— a single read-only statement only; writes and raw file-reader functions are rejected.
git clone https://github.com/Michael-WhiteCapData/tablebridge-mcp cd tablebridge-mcp uv pip install -e ".[dev]" ruff check . pytest # uses real DuckDB over temp files
Query local CSV, Parquet, JSON and TSV files with real SQL via DuckDB. Gives your AI coding tool ground-truth data access instead of hallucinated answers.
Official MCP server for dbt (data build tool) providing integration with dbt Core/Cloud CLI, project metadata discovery, model information, and semantic layer querying capabilities.
Query and analyze data with MotherDuck and local DuckDB
A collection of tools for managing the platform, addressing data quality and reading and writing to Teradata Database.
A read-only MCP server for Avro data sources, powered by the CData JDBC Driver.
Run SQL queries on data in Amazon S3 using AWS Athena.
Interact with Bauplan data tables and run queries.
Production-grade MCP server for Databricks: SQL Warehouses, Jobs API, multi-workspace support.
Visual no-code generator that turns any database into multiple scoped MCP servers — one per access group, with PII masking and fail-closed query scoping built in.
A read-only MCP server by CData that enables LLMs to query live data from EnterpriseDB databases.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
