Elasticsearch MCP server

The Elasticsearch Model Context Protocol (MCP) Server enables you to process data workflows and perform Elasticsearch operations through a Spring AI MCP-based interface. It allows external clients to interact with your Elasticsearch cluster using standard JSON-RPC communication.

Getting Started

Prerequisites

Before installing the Elasticsearch MCP Server, ensure you have:

• JDK 17 or later
• Running Elasticsearch instance (version 7.16 or later)
• An MCP client (such as Claude Desktop)

Installation

1. Clone the repository:

   git clone https://github.com/silbaram/elasticsearch-mcp-server.git
   cd elasticsearch-mcp-server
   

2. Configure your Elasticsearch connection by editing mcp-server/src/main/resources/application.yml:

   elasticsearch:
     version: "8.6.1"
     search:
       hosts:
         - http://localhost:9200
   

3. Build the project:

   ./gradlew build
   

   The JAR file will be generated in the mcp-server/build/libs/ directory.

Configuration

Setting Up Your MCP Client

1. Launch your MCP client (such as Claude Desktop)
2. Navigate to Settings > Developer > MCP Servers
3. Click "Edit Config" and add a new server configuration:

   {
     "mcpServers": {
       "elasticsearch-server": {
         "command": "java",
         "args": [
           "-Dusername=YOUR_USERNAME", 
           "-Dpassword=YOUR_PASSWORD",
           "-jar",
           "/path/to/your/mcp-server.jar" 
         ]
       }
     }
   }
   

Replace /path/to/your/mcp-server.jar with the actual path to your built JAR file. The username and password parameters are optional and only needed if your Elasticsearch cluster requires authentication.

Available Tools

The MCP server provides several tools for interacting with Elasticsearch:

Cluster Information

• get_cluster_health: Returns basic information about the Elasticsearch cluster status
• get_cluster_statistics: Retrieves comprehensive statistics including cluster name, UUID, status, and resource usage
• get_shard_allocation: Shows information about shard allocation across the cluster
• get_shard_allocation_for_node: Returns shard allocation for a specific node

Index Management

• get_cat_indices: Lists all indices in the Elasticsearch cluster
• get_cat_indices_by_name: Lists indices matching a specified name or pattern
• get_cat_aliases: Lists all aliases in Elasticsearch
• get_cat_aliases_by_name: Lists aliases matching a specified name or pattern
• get_cat_mappings: Retrieves field mapping information for a specific index

Document Operations

• get_document_search_by_index: Searches for documents within an index using AI-generated queryDSL

Usage Examples

Once your MCP client is configured to use the Elasticsearch MCP server, you can issue commands to interact with your Elasticsearch cluster.

Example: Check Cluster Health

You can ask your MCP client (like Claude) to check the health of your Elasticsearch cluster:

"Check the health of my Elasticsearch cluster"

Example: Search for Documents

You can perform document searches with natural language queries:

"Search for documents in my 'customers' index that mention 'premium subscription'"

The MCP server will translate this into an appropriate Elasticsearch query and return the results.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "elasticsearch-server" '{"command":"java","args":["-Dusername=YOUR_USERNAME","-Dpassword=YOUR_PASSWORD","-jar","/path/to/your/mcp-server.jar"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "elasticsearch-server": {
            "command": "java",
            "args": [
                "-Dusername=YOUR_USERNAME",
                "-Dpassword=YOUR_PASSWORD",
                "-jar",
                "/path/to/your/mcp-server.jar"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "elasticsearch-server": {
            "command": "java",
            "args": [
                "-Dusername=YOUR_USERNAME",
                "-Dpassword=YOUR_PASSWORD",
                "-jar",
                "/path/to/your/mcp-server.jar"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect