Elasticsearch MCP Server

What it does

This MCP server bridges AI agents to Elasticsearch clusters, enabling them to interact with indices using natural language. It allows agents to perform complex data retrieval and analysis without requiring the developer to write custom API integrations for every use case.

Tools

• list_indices: Retrieves a list of all available Elasticsearch indices.
• get_mappings: Fetches field mappings for a specific index to understand data structure.
• search: Executes searches using Elasticsearch Query DSL.
• esql: Runs ES|QL queries for advanced piped analysis.
• get_shards: Provides shard information for indices to monitor health and distribution.

Installation

Deploy via Docker using the following configuration in claude_desktop_config.json:

{
  "mcpServers": {
    "elasticsearch-mcp-server": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "ES_URL",
        "-e", "ES_API_KEY",
        "docker.elastic.co/mcp/elasticsearch",
        "stdio"
      ],
      "env": {
        "ES_URL": "<your-cluster-url>",
        "ES_API_KEY": "<your-api-key>"
      }
    }
  }
}

Supported hosts

• Claude Desktop
• Cursor
• VS Code