playbooks
Learn Cursor Rules Windsurf Rules MCPs Modes
Log in

Elasticsearch MCP server

Enables natural language interaction with Elasticsearch clusters for querying, indexing, and management operations via Docker-deployed infrastructure.
Back to servers
Setup instructions
Provider
cr7258
Release date
Jan 09, 2025
Language
Python
Stats
205 stars
View on GitHub

The Elasticsearch/OpenSearch MCP Server allows you to interact with Elasticsearch or OpenSearch clusters through the Model Context Protocol. It provides tools for searching documents, managing indices, and administering your cluster with a standardized interface.

Installation and Setup

Prerequisites

Before using the MCP server, you'll need an Elasticsearch or OpenSearch cluster. You can quickly start one 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

The default credentials are:

  • Elasticsearch: username elastic, password test123
  • OpenSearch: username admin, password admin

You can access Kibana or OpenSearch Dashboards at http://localhost:5601.

Environment Variables

Configure authentication using these environment variables:

Basic Authentication:

  • ELASTICSEARCH_USERNAME and ELASTICSEARCH_PASSWORD
  • OPENSEARCH_USERNAME and OPENSEARCH_PASSWORD

API Key Authentication (Elasticsearch only - Recommended):

  • ELASTICSEARCH_API_KEY: API key for Elasticsearch authentication

Additional Configuration:

  • ELASTICSEARCH_HOSTS / OPENSEARCH_HOSTS: Comma-separated list of hosts (default: https://localhost:9200)
  • ELASTICSEARCH_VERIFY_CERTS / OPENSEARCH_VERIFY_CERTS: Whether to verify SSL certificates (default: false)

Running the MCP Server

Option 1: Using uvx (Recommended)

Using uvx automatically installs the package from PyPI:

For Standard I/O (stdin/stdout)

Add the following configuration to Claude Desktop's config file (claude_desktop_config.json):

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

For Server-Sent Events (SSE)

# Set environment variables first
export ELASTICSEARCH_HOSTS="https://localhost:9200"
export ELASTICSEARCH_USERNAME="elastic"
export ELASTICSEARCH_PASSWORD="test123"

# Start the SSE server (default: http://127.0.0.1:8000/sse)
uvx elasticsearch-mcp-server --transport sse

# Or with custom host/port/path
uvx elasticsearch-mcp-server --transport sse --host 0.0.0.0 --port 8000 --path /sse

For Streamable HTTP

# Set environment variables first
export ELASTICSEARCH_HOSTS="https://localhost:9200"
export ELASTICSEARCH_USERNAME="elastic"
export ELASTICSEARCH_PASSWORD="test123"

# Start the HTTP server (default: http://127.0.0.1:8000/mcp)
uvx elasticsearch-mcp-server --transport streamable-http

# Or with custom host/port/path
uvx elasticsearch-mcp-server --transport streamable-http --host 0.0.0.0 --port 8000 --path /mcp

Option 2: Using uv with local development

If you're developing locally:

# For Standard I/O
uv --directory path/to/elasticsearch-mcp-server run elasticsearch-mcp-server

# For SSE
uv run src/server.py elasticsearch-mcp-server --transport sse

# For Streamable HTTP
uv run src/server.py elasticsearch-mcp-server --transport streamable-http

Available Features

General Operations

  • general_api_request: Execute any Elasticsearch/OpenSearch API endpoint

Index Operations

  • list_indices: List all indices
  • get_index: Get information about specific indices
  • create_index: Create a new index
  • delete_index: Delete an index
  • create_data_stream: Create a new data stream
  • get_data_stream: Get information about data streams
  • delete_data_stream: Delete data streams

Document Operations

  • search_documents: Search for documents
  • index_document: Create or update a document
  • get_document: Get a document by ID
  • delete_document: Delete a document by ID
  • delete_by_query: Delete documents matching a query

Cluster Operations

  • get_cluster_health: Get cluster health information
  • get_cluster_stats: Get cluster statistics

Alias Operations

  • list_aliases: List all aliases
  • get_alias: Get information about specific aliases
  • put_alias: Create or update an alias
  • delete_alias: Delete an alias

Elasticsearch Version Compatibility

The MCP server works with different Elasticsearch versions:

MCP Server Elasticsearch/OpenSearch
elasticsearch-mcp-server-es7 Elasticsearch 7.x
elasticsearch-mcp-server Elasticsearch 8.x
elasticsearch-mcp-server-es9 Elasticsearch 9.x
opensearch-mcp-server OpenSearch 1.x, 2.x, 3.x

To use a specific version, run the appropriate variant:

uvx elasticsearch-mcp-server-es7  # For Elasticsearch 7.x
uvx elasticsearch-mcp-server      # For Elasticsearch 8.x (default)
uvx elasticsearch-mcp-server-es9  # For Elasticsearch 9.x
uvx opensearch-mcp-server         # For OpenSearch

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

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

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

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later