Elasticsearch MCP server now available on AWS Marketplace

We’re excited to announce that the Elasticsearch Model Context Protocol (MCP) server is now available in the AWS Marketplace. 

Being listed under the AI Tools and Agents category ensures that customers can easily discover and deploy the Elasticsearch MCP server as a container on AWS.  Whether you're building AI copilots, intelligent agents, or advanced analytics platforms, Elastic has the foundation to power it.

With the MCP server, you can connect to Elasticsearch data directly from any MCP client, such as Claude Desktop or MCP Inspector or an agentic application. The MCP server makes it possible for AI agents or applications to access and interact with Elasticsearch through natural language conversations. The Elasticsearch MCP server is free to use, but infrastructure and Elasticsearch server costs may apply. 

Agents are the next step in the evolution of generative AI (GenAI) applications. They combine real-time information retrieval, reasoning, and tool usage to take meaningful actions. Agentic AI is not just about answering questions; it is also designed to act based on goals and context. The MCP servers manage one or more AI agents, such as large language models (LLMs) or tools that interpret natural language input. This reduces the need for DSL or ES|QL query, making business intelligence and operational data more accessible, encouraging self-service analytics, unifying access across multiple data sources, and abstracting connections to systems like Elasticsearch. This gives agents real-time, reliable access to your business knowledge and long-term memory. 

With Amazon Bedrock models like Anthropic’s Claude supporting MCP clients, deploying intelligent, data-aware agents is now easier and more powerful than ever.

Elastic continues to lead the way in Search AI, delivering advanced capabilities that power intelligent applications, including:

• Vector search for semantic and similarity-based search experiences

• Hybrid search that combines semantic (vector) and lexical (keyword) search for greater accuracy

• Retrieval augmented generation (RAG) to enhance LLM responses with relevant and contextual data

• Real-time AI observability to monitor model and system behavior in production environments

• AI-powered security solutions that detect attacks, recommend mitigation steps, and automate threat discovery and response with attack pattern recognition and import capabilities

These tools are helping teams build intelligent, Search AI powered applications with context-aware AI responses.

Elastic was honored to receive the AWS Global Generative AI Infrastructure and Data Partner of the Year Award. This award recognizes top technology partners with the Generative AI Competency that support vector embeddings and data storage and management.

This recognition highlights our joint investment, innovation, and co-engineering with AWS and how our collaboration helps customers develop and scale their GenAI capabilities.

The release and timing of any features or functionality described in this post remain at Elastic's sole discretion. Any features or functionality not currently available may not be delivered on time or at all.

In this blog post, we may have used or referred to third party generative AI tools, which are owned and operated by their respective owners. Elastic does not have any control over the third party tools and we have no responsibility or liability for their content, operation or use, nor for any loss or damage that may arise from your use of such tools. Please exercise caution when using AI tools with personal, sensitive or confidential information. Any data you submit may be used for AI training or other purposes. There is no guarantee that information you provide will be kept secure or confidential. You should familiarize yourself with the privacy practices and terms of use of any generative AI tools prior to use. 

Elastic, Elasticsearch, and associated marks are trademarks, logos, or registered trademarks of Elasticsearch N.V. in the United States and other countries. All other company and product names are trademarks, logos, or registered trademarks of their respective owners.