Spark SQL
Query Spark SQL clusters via Thrift/HiveServer2. Works with Spark, EMR, Hive, Impala
What you can do with it
Share of each task's required capabilities it coversPrefer a ready-made agent?
An MCP server is a connector for your own assistant. These finished products do the job for you: query databases in plain language.Similar tools
Listed for the same task: query databases in plain languageReviews
No review yet. Used Spark SQL? Be the first to help others choose.What it does
Spark SQL is an MCP server, a connector that lets an AI assistant use it as a tool. It is installed locally as a package and runs on your machine.
From the publisher's description, Electra Index matched it to one capability: sql querying. That makes it a candidate for tasks such as query databases in plain language or build data pipelines.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.
At a glance
How to connect
As declared in the Official MCP Registry · not tested by Electra IndexInstall package
- PYPI
spark-sql-mcp-serverv0.1.2 · runs locally (stdio)
Required: SPARK_HOST (get it from the publisher)
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"spark-sql": {
"command": "uvx",
"args": [
"spark-sql-mcp-server"
],
"env": {
"SPARK_HOST": "<your SPARK_HOST>"
}
}
}
}Replace the values in <angle brackets>.
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Install package | spark-sql-mcp-server | DECLARED | SRC-001 Official MCP Registry | 4d ago |
| Package registries | pypi | DECLARED | SRC-001 Official MCP Registry | 4d ago |
| Local install (package) | yes | DECLARED | SRC-001 Official MCP Registry | 4d ago |
| Remote access (hosted) | no | DECLARED | SRC-001 Official MCP Registry | 4d ago |
| Repository | https://github.com/aidancorrell/spark-sql-mcp-server | DECLARED | SRC-001 Official MCP Registry | 4d ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 4d ago |
| Version | 0.1.2 | DECLARED | SRC-001 Official MCP Registry | 4d ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 4d ago |
Change history
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is Spark SQL still online?
Free alerts · no account▲ 0Do you publish Spark SQL? Get it seen by people choosing a tool
For publishers · optionalLaunch Spotlight: 60 days of clearly labelled Sponsored visibility on the use-case pages where Spark SQL already appears, plus the weekly Pulse. No click in 60 days? The next 60 days are free.
Sponsored placements never change a score or a rank.
Questions about Spark SQL
How do I connect Spark SQL?
Install the PyPI package spark-sql-mcp-server. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.
Does Spark SQL need an API key or token?
Yes. The registry entry lists a required value: SPARK_HOST. Get it from the publisher.
What can I use Spark SQL for?
Based on its description, it is most relevant to: query databases in plain language, build data pipelines.