Tablebridge MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 43 installs a week from pypi.
Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.
The linked repository no longer exists on GitHub — it was deleted or made private.
What the code does
We have not read this server's code yet, 20 d ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
этот файл ставится пользователю, но в репозитории его нет
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add tablebridge-mcp -- uvx tablebridge{
"mcpServers": {
"tablebridge-mcp": {
"command": "uvx",
"args": [
"tablebridge"
]
}
}
}[mcp_servers.tablebridge-mcp]
command = "uvx"
args = ["tablebridge"]{
"mcpServers": {
"tablebridge-mcp": {
"command": "uvx",
"args": [
"tablebridge"
]
}
}
}{
"servers": {
"tablebridge-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"tablebridge"
]
}
}
}Optional settings from the registry entry, left out of the block above:
TABLEBRIDGE_DATA_DIR (Directory of data files to expose as SQL tables (sandboxed)), TABLEBRIDGE_MAX_ROWS (Maximum rows returned per query/preview), TABLEBRIDGE_RECURSIVE (Scan subdirectories too (1/0)).
Alternatives to Tablebridge MCP
same job, measured the same wayLocal data runtime for AI agents: query CSV, Excel, Parquet and JSON files with DuckDB SQL.
Every spreadsheet is a table: Excel, CSV, Parquet and JSON as SQL tables for AI agents.
Read-only WHOOP v2 data for MCP clients, with local SQLite cache and CSV/JSONL/Parquet exports.
Create interactive visualizations and query data sources (SQLite, CSV, Parquet, JSON)
Share a folder of data files read-only over MCP, and fill it from PostgreSQL under a read-only role.
Read-only SQL on CSV files for AI agents. No writes, no network; --root confines file access.
Read and filter Excel, ODS, CSV, SQLite, Parquet and MTSV files — or a directory — as plain text
Read-only SQL querying + schema introspection over Postgres & SQLite, with a gated write mode.
Tablebridge MCP — questions
Answers built from our own checks of this server.