Elasticsearch MCP

The Elasticsearch MCP Server connects AI agents to Elasticsearch data using the Model Context Protocol. It enables natural language interactions with Elasticsearch indices, allowing agents to query, analyze, and retrieve data without custom APIs.

Note: This server is deprecated and will only receive critical security updates. It has been superseded by the Elastic Agent Builder MCP endpoint available in Elastic 9.2.0+ and Elasticsearch Serverless projects.

Features

• List all available Elasticsearch indices
• Get field mappings for specific indices
• Perform searches using Elasticsearch query DSL
• Execute ES|QL queries
• Get shard information for indices
• Supports Elasticsearch versions 8.x and 9.x

Protocols

Supports both stdio (direct client connections) and streamable-HTTP (web-based integrations) protocols.

Authentication

Supports two authentication methods:

• API key authentication (recommended)
• Username and password authentication

Tools

• list_indices: List all available Elasticsearch indices
• get_mappings: Get field mappings for a specific Elasticsearch index
• search: Perform an Elasticsearch search using query DSL
• esql: Execute an ES|QL query
• get_shards: Get shard information for all or specific indices

Security

• Credentials stored only in environment variables
• HTTPS communication with Elasticsearch when using https:// URLs
• No local data persistence
• Optional SSL/TLS certificate verification skip for development environments