PySpark MCP Server

by annasmazhar Your server? Claim it

local only

PySpark MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 92 installs a week from pypi. Last commit 26 Oct 2026.

SQL migration, AWS Glue job generation, and PySpark optimization as an MCP server.

Installs per day peak 94 · avg 21 · -50% w/w

a month agotoday

Installs / week

pypi · pyspark-tools

Stars

0 open issues

26 Oct 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check PySpark MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add pyspark-mcp -- uvx pyspark-tools

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "pyspark-mcp": {
      "command": "uvx",
      "args": [
        "pyspark-tools"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.pyspark-mcp]
command = "uvx"
args = ["pyspark-tools"]

.cursor/mcp.json

{
  "mcpServers": {
    "pyspark-mcp": {
      "command": "uvx",
      "args": [
        "pyspark-tools"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "pyspark-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pyspark-tools"
      ]
    }
  }
}

Alternatives to PySpark MCP

same job, measured the same way

SQLBot MCP Proxy

by wenrou21

MCP server proxy for SQLBot Text-to-SQL queries and report generation.

local only

Mssql Writer

by connorbritain

MCP server for Microsoft SQL Server — read and data write operations, no DDL

116 installs/wk local only

Orionbelt Analytics

by ralfbecher

Ontology-based MCP server for database schema analysis and RDF/OWL ontology generation

657 installs/wk local only

Metabase AI Assistant

by enessari

MCP Server for Metabase - 111 tools for SQL generation, dashboards & PostgreSQL

53 installs/wk local only

Database

by rog0x

SQL formatting, schema visualization, migration generation

37 installs/wk local only

BioMCP-TS

by yeyuan98

Biomedical MCP server: genes, variants, trials, literature, patents, optional SQL/R/biowasm tools.

956 installs/wk local only

Database Admin

by cybeleri

Database admin MCP: schema inspection, query optimization for PostgreSQL and MySQL

43 installs/wk local only

MCP Sqlite Tools

by spences10

MCP server for local SQLite database operations

107 installs/wk local only

PySpark MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for PySpark MCP?

PySpark MCP 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 pyspark-tools was installed 92 times last week.

How do I connect PySpark MCP?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls pyspark-tools straight from pypi; nothing to host, nothing to sign up for.

How many people use PySpark MCP?

The pypi package pyspark-tools was installed 92 times in the last week. Week over week that is -50%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is PySpark MCP open source?

Yes — it is published under the MIT licence, written in Python and 0 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.