Elasticsearch MCP server for AI agents

The Elasticsearch/OpenSearch MCP Server enables seamless interaction with Elasticsearch and OpenSearch databases through the Model Context Protocol. It provides tools for searching documents, analyzing indices, and managing clusters directly from AI assistants like Claude.

Features and Capabilities

General Operations

Perform general HTTP API requests for any Elasticsearch/OpenSearch API
Execute specialized operations for indices, documents, clusters, and aliases

Index Management

List all indices
Get index information (mappings, settings, aliases)
Create new indices
Delete existing indices

Document Operations

Search documents with complex queries
Create or update documents
Retrieve documents by ID
Delete documents individually or by query

Cluster and Alias Management

Monitor cluster health and statistics
List and manage aliases
Create, update, and delete aliases for specific indices

Installation

Prerequisites

Docker and Docker Compose installed
Node.js (for Smithery installation method)
Python with uv/uvx available

Starting Elasticsearch/OpenSearch

Create an environment configuration file:
```
cp .env.example .env
```
Start the database using Docker Compose:
```
# For Elasticsearch
docker-compose -f docker-compose-elasticsearch.yml up -d

# For OpenSearch
docker-compose -f docker-compose-opensearch.yml up -d
```
Default credentials:
- Elasticsearch: username elastic, password test123
- OpenSearch: username admin, password admin
Access the dashboard at http://localhost:5601

Configuring with Claude Desktop

Method 1: Installing via Smithery

npx -y @smithery/cli install elasticsearch-mcp-server --client claude

Method 2: Using uvx

Add the following to your Claude Desktop configuration file:

// For Elasticsearch
{
  "mcpServers": {
    "elasticsearch-mcp-server": {
      "command": "uvx",
      "args": [
        "elasticsearch-mcp-server"
      ],
      "env": {
        "ELASTICSEARCH_HOSTS": "https://localhost:9200",
        "ELASTICSEARCH_USERNAME": "elastic",
        "ELASTICSEARCH_PASSWORD": "test123"
      }
    }
  }
}

// For OpenSearch
{
  "mcpServers": {
    "opensearch-mcp-server": {
      "command": "uvx",
      "args": [
        "opensearch-mcp-server"
      ],
      "env": {
        "OPENSEARCH_HOSTS": "https://localhost:9200",
        "OPENSEARCH_USERNAME": "admin",
        "OPENSEARCH_PASSWORD": "admin"
      }
    }
  }
}

Method 3: Using uv with local source code

// For Elasticsearch
{
  "mcpServers": {
    "elasticsearch-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/src/elasticsearch_mcp_server",
        "run",
        "elasticsearch-mcp-server"
      ],
      "env": {
        "ELASTICSEARCH_HOSTS": "https://localhost:9200",
        "ELASTICSEARCH_USERNAME": "elastic",
        "ELASTICSEARCH_PASSWORD": "test123"
      }
    }
  }
}

Configuration file locations:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

Remember to restart Claude Desktop after configuration changes.

Using the MCP Server

Once configured, you can interact with Elasticsearch/OpenSearch using natural language commands in Claude:

"List all indices in the cluster"
"How old is the student Bob?" (to search for student data)
"Show me the cluster health status"
"Create a new index called customers with a field for email addresses"
"Search for documents containing the word 'error' in the logs index"

The MCP server translates these natural language requests into the appropriate Elasticsearch/OpenSearch API calls and returns the results.

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.