Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.
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.
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.
tablebridge on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Everything the assistant can do here goes through one of these:
list_sources — List the tables (one per data file) with column counts — start heredescribe — A table's columns and typespreview — First N rows of a tablequery — Run read-only SQL (DuckDB dialect) across the tables, JOINs includedrefresh — Re-scan the data directory for added/changed filesserver_info — Effective config (data dir, row cap, supported formats)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.
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.
| Tool | What it does |
|---|---|
| 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) |
{
"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.
| Variable | Description | Required |
|---|---|---|
| TABLEBRIDGE_DATA_DIR | Filesystem location the server is allowed to use. | Optional |
Read-only SQL access to Postgres — let your assistant inspect schemas and answer questions from real data.
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Official MongoDB server covering data, schemas and Atlas management — from find queries to spinning up clusters.
Serverless Postgres with database branching — point your assistant at Neon and let it work on disposable copies.