mcpbeat Sign in

Spark SQL MCP Server

by aidancorrell Your server? Claim it
local only

Spark SQL runs on your own machine — the client starts it, so there is no endpoint to ping. 59 installs a week from pypi. Last commit 9 Feb 2026.

Query Spark SQL clusters via Thrift/HiveServer2. Works with Spark, EMR, Hive, Impala.

Installs per day peak 25 · avg 12 · -28% w/w
a month agotoday
59
Installs / week
pypi · spark-sql-mcp-server
1
Stars
0 open issues
9 Feb 2026
Last commit
0 releases in 90 days
MIT
License
Python

What the code does

We read the source, 16 h ago · rules 3dff92dd89df

Capabilities

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.

Builds a database query by concatenation [пакет] .github/workflows/changelog.yml:40, .github/workflows/changelog.yml:40
      - name: Update CHANGELOG.md
        env:
          PR_TITLE: ${{ github.event.pull_request.title }}

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.

Three servers free · no card

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.

run in your terminal
claude mcp add spark-sql-mcp-server -- uvx spark-sql-mcp-server
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "spark-sql-mcp-server": {
      "args": [
        "spark-sql-mcp-server"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.spark-sql-mcp-server]
command = "uvx"
args = ["spark-sql-mcp-server"]
.cursor/mcp.json
{
  "mcpServers": {
    "spark-sql-mcp-server": {
      "args": [
        "spark-sql-mcp-server"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "spark-sql-mcp-server": {
      "args": [
        "spark-sql-mcp-server"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: SPARK_HOST (Hostname of the Spark Thrift Server), SPARK_PORT (Port of the Spark Thrift Server (default: 10000)), SPARK_DATABASE (Default database to use), SPARK_AUTH (Authentication method: NONE, LDAP, KERBEROS, CUSTOM, or NOSASL), SPARK_USERNAME (Username for LDAP authentication), SPARK_PASSWORD (Password for LDAP authentication), SPARK_KERBEROS_SERVICE_NAME (Kerberos service name (default: hive)). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Spark SQL

same job, measured the same way
Surrealdb MCP
by mrfentmen

MCP server for SurrealDB: version check, SQL queries. Works with any instance.

local only
C
Cluster Validator
by detentpoint

Read-only health validation for Windows Server failover clusters running SQL Server FCI.

local only
Hasura MCP
by mrfentmen

MCP server for Hasura: metadata export, SQL passthrough. Works with any self-hosted instance.

local only
Mysql
by codechap

MCP server for MySQL/MariaDB — pooled async queries with destructive-query safety

local only
csvql
by melihbirim

Query CSV files with SQL via MCP. Fast, local, zero-config, read-only, sandboxable with --root.

local only
MCP Trino
by tuannvm

MCP server for Trino distributed SQL query engine access

local only
SQL Benchmarks Lab
by rctruta

Query pre-computed SQL engine benchmarks. Runs standalone, no server setup required.

45 installs/wk local only
StackQL MCP Server
by stackql

SQL-native query and provisioning engine for cloud infrastructure, served over MCP.

186 installs/wk local only

Spark SQL — questions

Answers built from our own checks of this server.

Why is there no uptime for Spark SQL?
Spark SQL runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package spark-sql-mcp-server was installed 59 times last week.
How do I connect Spark SQL?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls spark-sql-mcp-server straight from pypi; nothing to host, nothing to sign up for.
How many people use Spark SQL?
The pypi package spark-sql-mcp-server was installed 59 times in the last week. Week over week that is -28%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Spark SQL open source?
Yes — it is published under the MIT licence, written in Python and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.