MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP Server and CLI for Apache Spark History Server. Debug Spark applications from AI agents, scripts, or the terminal.
pypi Apache-2.0 ★ 207 -
This read-only MCP Server allows you to connect to Apache Spark data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).
MIT -
Apache Spark installer and cluster manager (local or over SSH) with an MCP server for AI assistants
-
spark-ui-mcpgithub.com/pcosmin/spark-ui-mcpupdated this year
MCP server for Apache Spark UI REST API — inspect jobs, stages, SQL executions, executors and more. Supports SOCKS5 proxy for Kubernetes clusters.
npm MIT -
MCP server exposing Apache Spark event-log diagnostics over stdio.
npm MIT -
@dataflint/mcp-servergithub.com/dataflint/vscode-extensionupdated this year
DataFlint MCP Server Core - Model Context Protocol server for Apache Spark optimization
npm SEE LICENSE IN LICENSE -
Cloudera AI blueprint for governing agent access to Spark, Hive, and Impala through MCP, Knox, and Apache Ranger.
Apache-2.0 ★ 1 -
Spark-History-MCP-LangGraph-AI-Agentgithub.com/Kacper0199/Spark-History-MCP-LangGraph-AI-Agentupdated this year
This repository provides a complete infrastructure and an AI Agent for analyzing Apache Spark application logs using natural language.
-
Data pipelines aren't AI-ready until they are governed: this Databricks framework powered by Apache Spark and PySpark uses Unity Catalog and Delta Lake to serve verified, audit-ready data products through strict read-only MCP boundaries.
MIT -
EcomIQ-AI-Powered-Operational-Intelligence-Platform-github.com/Kaustubh-Indulkar/EcomIQ-AI-Powered-Operational-Intelligence-Platform-updated this year
EcomIQ is an AI-powered operational intelligence platform that combines Apache Kafka, Spark Structured Streaming, and PostgreSQL to process real-time e-commerce data. It leverages FastAPI, Google Gemini, and FastMCP to deliver conversational business insights through natural language queries.
-
spark-advisor-mcpgithub.com/pstysz/spark-advisorupdated this year
MCP server exposing spark-advisor tools for Claude Desktop and other MCP clients
pypi Apache-2.0 -
Real-time transaction fraud detection: Kafka + Spark Structured Streaming + NVIDIA NIM explanations + MCP risk-status tool
-
OmniData-MCPgithub.com/MostafaAI10/OmniData-MCPupdated this year
Unified MCP server for data engineering & analytics lets LLMs query, profile, transform, and visualize data via DuckDB and PySpark, with read-only guardrails and local audit logging.
MIT ★ 1 -
Real-time streaming data contract gatekeeper & zero-trust Delta Lake quarantine engine. Features PySpark Structured Streaming, Kafka (KRaft), Model Context Protocol (MCP) shift-left validation, dbt/DuckDB analytics marts, and automated LLM incident triage handling 40K+ events/sec with sub-millisecond latency.
MIT -
Agentic eCommerce Governed Retail Analytics Lakehouse on Databricks: includes OLTP orders, star-schema ETL with change data capture, Unity Catalog metrics, and Genie ontology agents for analytics and fraud. MCP Server, Databricks Genie Agents, non-Databricks Agents using LangGraph and Google ADK, PySpark, FastAPI, and GitHub Actions.
Apache-2.0