Spark SQL vs Tabularis
A side-by-side look at the Spark SQL and Tabularis MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
T
TabularisDatabasesOpen-source desktop SQL workspace with 3 built-in database drivers and 16 shipped plugins, including SQL Server, DuckDB, ClickHouse and Redis. Built-in MCP server for Claude, Cursor and Devin, SQL notebooks and visual EXPLAIN.59GoodAuth: no auth requiredVerdict: choose Spark SQL for databases work as a local process; choose Tabularis for databases. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Spark SQL when
- You need dedicated capabilities in the Databases domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
SPARK_HOST, SPARK_PORT, SPARK_DATABASE, SPARK_AUTH, SPARK_USERNAME, SPARK_PASSWORD, SPARK_KERBEROS_SERVICE_NAME. - You want tools like
list_databases, list_tables, describe_table.
TChoose Tabularis when
- You need dedicated capabilities in the Databases domain.
- Its auth model fits you: No auth required.
- You want tools like
list_connections, list_databases, list_tables.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | T Tabularis | |
|---|---|---|
| Category | Databases | Databases |
| Quality signal | 47/100 · Fair | 59/100 · Good |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | SPARK_HOSTSPARK_PORTSPARK_DATABASESPARK_AUTHSPARK_USERNAMESPARK_PASSWORDSPARK_KERBEROS_SERVICE_NAME | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 1 | 5,256 |
| Directory activity | 2 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 4 | 5 |
| Full listing | View Spark SQL | View Tabularis |
Tools & capabilities
Spark SQL tools 4
list_databasesList all available databaseslist_tablesList tables in a databasedescribe_tableGet table schema (columns, types)execute_queryRun read-only SQL queries with formatted results
Tabularis tools 5
list_connectionsList all saved database connectionslist_databasesList all databases available for a connectionlist_tablesList tables in a connection (with optional schema filter)describe_tableGet full schema: columns, indexes, foreign keysrun_queryExecute any SQL query and return results
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Spark SQL
{
"mcpServers": {
"spark-sql": {
"command": "uvx",
"args": [
"spark-sql-mcp-server"
],
"env": {
"SPARK_HOST": "YOUR_SPARK_HOST_HERE",
"SPARK_PORT": "YOUR_SPARK_PORT_HERE",
"SPARK_DATABASE": "YOUR_SPARK_DATABASE_HERE",
"SPARK_AUTH": "YOUR_SPARK_AUTH_HERE",
"SPARK_USERNAME": "YOUR_SPARK_USERNAME_HERE",
"SPARK_PASSWORD": "YOUR_SPARK_PASSWORD_HERE",
"SPARK_KERBEROS_SERVICE_NAME": "YOUR_SPARK_KERBEROS_SERVICE_NAME_HERE"
}
}
}
}
Tabularis
No confirmed install command for Tabularis yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
Spark SQL is categorized under Databases and uses a local stdio subprocess. Tabularis belongs to Databases and uses an install path we have not confirmed yet. Pick Spark SQL for databases work and Tabularis for databases.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. Tabularis has no confirmed install command yet — follow its own setup instructions.
Spark SQL has no declared pricing — check the project's own site. Tabularis is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add spark-sql and tabularis as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Spark SQL has a quality signal of 47/100 (Fair) with 2 views, 0 installs and 1 GitHub stars. Tabularis has 59/100 (Good) with 1 views, 0 installs and 5,256 GitHub stars.