OpenSearch MCP Server is a Model Context Protocol (MCP) server for OpenSearch that enables AI assistants to interact with OpenSearch clusters. It exposes a standardized MCP interface allowing AI models to perform core OpenSearch operations such as searching indices, retrieving mappings, listing indices, and shard management through both stdio and streaming transports (SSE and Streamable HTTP). The server ships with built-in core tools (enabled by default) for common tasks and supports additional tools (disabled by default) that can be enabled as needed via a tool filter. Tools expose configurable parameters for OpenSearch connections and operations (e.g., opensearch_url, index, body) and include a flexible GenericOpenSearchApiTool to call arbitrary endpoints, reducing tool proliferation. It integrates seamlessly with Claude Desktop and LangChain, and offers secure authentication via basic auth or IAM roles. Comprehensive usage and configuration guidance are provided in the User Guide, with development guidance in the Developer Guide. The project envisions ongoing expansion with more tools and capabilities.