"Apache Parquet" matching MCP servers:

Provides safe, deterministic inspection, transformation, validation, and diffing of structured data (JSON, CSV, YAML, Parquet) via schema-aware MCP tools.

Enables inspection and management of Apache Airflow DAGs, runs, and logs across multiple instances. It provides tools for monitoring workflows and performing gated write operations like triggering DAGs or clearing task instances.

Connects LLM agents to Apache Atlas for searching, tracing lineage, and managing metadata. Read-only by default, with optional write mode for creating entities and classifications.

Enables lookups across Apache Iceberg Javadocs, local source evidence, and Iceberg REST Catalog operations through MCP tools and prompts.

Enables LLM agents to query Apache Hive/HiveServer2 by listing tables and running read-only SQL, with results returned as JSON.

Official MCP server for Apache Drill, enabling read-only SQL queries and inspection of schemas, storage plugins, and cluster/query state.

An MCP server that enables users to interact with Apache Doris databases through natural language, supporting query and management operations.

Enables Claude to analyze local CSV or Parquet files, handling larger datasets without uploading full files.

Enables natural-language data analysis by loading and inspecting datasets in CSV, JSON, Excel, and Parquet formats, with session management and secure file handling.

A Model Context Protocol server that provides seamless access to multiple storage services including S3, Azure Blob Storage, and Google Cloud Storage through Apache OpenDAL™.

Enables analysis of CSV and Parquet files by providing summaries of row and column counts. Includes sample data and tools for easy integration.

MCP server that diagnoses Apache Spark job failures and optimizes performance using stack-trace analysis and LLM providers, supporting EMR and local sources.

Enables read-only SQL querying and exploration of data files (CSV, Parquet, JSON, Excel, etc.) via DuckDB, supporting local paths, globs, URLs, and S3 buckets.

MCP server that integrates Apache Ranger authorization with RAG, enforcing Ranger policies to control access to knowledge bases before forwarding queries to RAG Studio.

The accountability layer for AI agents — a named human's signed yes before an agent does anything irreversible (payment, record change, deploy), then an offline-verifiable Trust Receipt. Apache-2.0, formally verified.

Sovereign, encrypted, persistent memory for AI agents. Eight MCP tools — remember, recall, forget (GDPR Art. 17 erasure), share, governance. Anchored on COTI V2 mainnet. Apache-2.0.

Enables natural-language querying of large Excel, Access, and Parquet datasets, returning executed SQL with results for verification. Exposes tools for status checking, table listing, and asking questions through MCP.

An MCP server that converts Apache Airflow DAGs into Prefect flows. It provides tools to read DAGs, lookup translation knowledge, validate code, search Prefect docs, scaffold projects, deploy, and generate migration reports.

Provides full-text search and retrieval tools for Apache Spark documentation using SQLite FTS5 with BM25 ranking. It enables AI assistants to efficiently search, filter by section, and read specific Spark documentation pages.

MCP server that profiles local data files (CSV, Parquet, JSON, Excel) and returns compact structured summaries with data-quality flags, enabling AI agents to understand datasets without seeing raw rows.