Tabellum

dev.dudkoPublished by dudko.devv0.1.2Updated Oct 25, 2026

MCP bridge to the Tabellum database client: schema, reads, SQL drafts; writes approved in the app.

The publisher's own server: PDF to Markdown

VerifiedSTDIODesktop onlyDatabasesDeveloper Tools

Overview

AI-generated overview

Bridges an AI assistant to the Tabellum desktop database client so it can inspect schemas, run reads and draft SQL, with writes approved in the app.

What you can do
  • Inspect connections, schemas, objects, users and sample rows
  • Run read-only queries and explain plans; open editor tabs and type SQL drafts
  • Propose writes, DDL and admin statements that wait for your click in the app
  • Compare schemas against another connection or a saved snapshot and generate migration statements
  • List, read and propose dashboards and schema designs
When to use it
Useful when you work in the Tabellum desktop client for PostgreSQL, MySQL/MariaDB, SQL Server or BigQuery and want an assistant to explore schemas, draft queries and suggest migrations while you keep control of anything that changes data.
Requirements
The Tabellum desktop app must be installed and running on macOS, Windows or Linux; the npm package runs on Node.js 24+ and is started via npx. The shim reads the app's local port and per-install token from a config file in the user's home directory, so no keys are set by hand.
Before you install
The assistant can read schema details, users and roles, and sample rows where row sharing is enabled per connection. Writes, DDL and admin statements are only proposed and need your approval in the app, and expire after 10 minutes. Calls are attributed in the app's agent log; regenerating the token requires restarting the MCP server.

Installation

In SourceWeft

  1. Open Tabellum in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Tabellum — MCP setup

Let your AI assistant work with your databases through Tabellum, a desktop database client for PostgreSQL, MySQL/MariaDB, SQL Server and BigQuery. The MCP server is hosted by the running app on your machine; this package is a small stdio shim that forwards to it. Queries the assistant writes appear live in the editor, and nothing that changes data runs without your click in the app.

  • Server: tabellum
  • Transport: stdio (local process)
  • Package: @dudko.dev/tabellum-mcp — Node.js 24+
  • Auth: a per-install token the app generates; the shim reads it for you from ~/.tabellum/mcp.json.

What you can do

With the Tabellum app open, the assistant gets the same tools as the app's own agent — the app serves them, so the list follows the app version. Reads run at once; anything that writes waits for your click in the app.

ToolWhat it does
Look around
list_connectionsConnection names, drivers, read-only flags. No hosts, no users.
describe_schemaEvery schema of a connection with its table, view, function, procedure and sequence names.
describe_objectColumns, indexes, constraints and the CREATE of one object.
list_usersUsers and roles with their flags, where the database lists them.
sample_rowsUp to N rows of a table — only where the connection shares rows.
Query
run_readRuns a statement only if the engine classifies it as a read; anything else answers needs_approval.
explainThe estimated plan of a read; nothing runs.
propose_writeA write, DDL or admin statement for your approval in the app (10-minute timeout).
open_editor_tabOpen a query tab bound to a connection.
draft_to_editorType SQL into a tab while you watch, without running it.
Compare schemas
compare_schemasDiff a connection against another or a saved snapshot; with migration: true, the statements that close the gap. Nothing runs.
save_schema_snapshot / list_schema_snapshotsSave a connection's schema to the workspace; list the snapshots.
Dashboards
list_dashboards / get_dashboardThe workspace's dashboards; one dashboard's file and panels.
propose_dashboardA new or changed dashboard — you see the diff and apply it.
Schema designs
list_designs / get_designThe workspace's schema designs; one design's file and objects.
propose_designA new or changed design — you see what is added, changed and removed. Nothing runs against a database.
describe_featureThe file format and rules of designer, dashboards or schema_compare, read before proposing one.

Resources, for clients that prefer them: tabellum://connections, tabellum://schema/<connection>, tabellum://snapshots, tabellum://dashboards, tabellum://designs. Every call is attributed in the app — a badge on the tab and a line in the agent log.


Install in Claude Code (plugin)

/plugin marketplace add dudko-dev/tabellum-mcp-setup/plugin install tabellum@tabellum/reload-plugins

Start the Tabellum app first (macOS, Windows or Linux). The shim reads the app's local port and token from ~/.tabellum/mcp.json, written while the app runs; with the app closed every call answers "Tabellum is not running".

Prefer not to use the marketplace? Add the server directly:

claude mcp add tabellum -- npx -y @dudko.dev/tabellum-mcp

Connect from other clients

Claude Desktop

claude_desktop_config.json (Settings → Developer → Edit Config):

json
{  "mcpServers": {    "tabellum": {      "command": "npx",      "args": [        "-y",        "@dudko.dev/tabellum-mcp"      ]    }  }}

Cursor

~/.cursor/mcp.json or .cursor/mcp.json:

json
{  "mcpServers": {    "tabellum": {      "command": "npx",      "args": [        "-y",        "@dudko.dev/tabellum-mcp"      ]    }  }}

VS Code (GitHub Copilot / MCP) and other clients

json
{  "servers": {    "tabellum": {      "type": "stdio",      "command": "npx",      "args": [        "-y",        "@dudko.dev/tabellum-mcp"      ]    }  }}

Safety

  • The engine classifies, you approve. Every statement is classified by the app's parser; anything that is not a read goes through propose_write and waits for your click. A label claimed by the model never overrides it.
  • Loopback only. The app listens on 127.0.0.1 with a per-install bearer token (Settings → Agents shows it and can regenerate it).
  • Row data is opt-in per connection. sample_rows returns rows only where you enabled sharing for that connection.

Troubleshooting

  • "Tabellum is not running" — open the app, then retry.
  • Unauthorized after regenerating the token — restart the MCP server in your client so the shim re-reads ~/.tabellum/mcp.json.
  • A write seems stuck — it is waiting for approval in the app; after 10 minutes it returns declined: timeout.

Support

Source: README.md at commit a740b59

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the server did not complete the MCP handshake.

Version history

2
  1. v0.1.2LatestOct 25, 2026
  2. v0.1.1Sep 26, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Dudko integrations