MCP Sunucuları

Provides AI agents with access to ClickHouse analytical databases through the Model Context Protocol. Enables running analytical queries, exploring table schemas, inspecting materialized views, and monitoring query performance. Designed for OLAP workloads with support for large result sets and query profiling.

Official Elastic MCP server that connects AI agents to Elasticsearch data using the Model Context Protocol. Enables natural language interactions with Elasticsearch indices — querying, analyzing, and retrieving data without custom APIs. Supports both stdio and streamable-HTTP transports, and works with Elasticsearch 8.x/9.x clusters including Elasticsearch Serverless. Distributed as a Docker container image from the Elastic registry.

Model Context Protocol üzerinden PostgreSQL veritabanlarına salt okunur erişim sağlar. AI agent'ların veritabanı şemalarını incelemesine, SELECT sorguları çalıştırmasına ve tablo yapılarını keşfetmesine olanak tanır. Verilerin yanlışlıkla değiştirilmesini önlemek için salt okunur transaction isolation kullanır. Daha önce referans sunucu paketinin parçasıydı; artık arşivlenmiştir ve servers-archived altında bulunur.

A Model Context Protocol server that provides a natural-language interface for LLMs and agents to manage, monitor, and query data in CockroachDB. Supports schema exploration, query plan inspection, and running SQL, with a read-only-by-default posture so agents can investigate a distributed SQL cluster safely.

The official OpenSearch Model Context Protocol server, enabling AI assistants to interact with OpenSearch clusters. Lets agents list indices, inspect mappings, run search and aggregation queries, and read basic cluster health so they can explore and analyze data stored in OpenSearch through natural language.

A Model Context Protocol server for working with large Oracle databases. It provides contextual schema information for databases with thousands of tables, letting AI assistants understand relationships, look up table and column definitions, and run queries without loading the entire schema into context.