Unofficial Elasticsearch MCP Server

by zx8086

9.1k downloads Not rated yet Apache-2.0 license

About

A production-ready Model Context Protocol (MCP) server that connects AI assistants like Claude Desktop to Elasticsearch clusters. This server provides comprehensive Elasticsearch operations through natural language interactions.

Details

License
Apache-2.0 license

Explore

- 🔧 Comprehensive Tooling: 60+ Elasticsearch operations including search, indexing, cluster management, and analytics
- ⚙️ Advanced Configuration: Type-safe configuration system with environment variable validation
- 🔒 Security Controls: Read-only mode with strict/warning options for safe production monitoring
- 📊 Rich Search: Advanced search with automatic highlighting, aggregations, and SQL support
- 🔄 Bulk Operations: Efficient bulk indexing, updating, and deletion with helper APIs
- 📈 Cluster Monitoring: Health checks, node statistics, and performance metrics
- 🛡️ Error Handling: Robust error handling with detailed logging and troubleshooting guides
- ⚡ Performance: Built on Bun runtime for optimal performance and modern JavaScript features

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Unofficial Elasticsearch MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "unofficial elasticsearch mcp server": {
            "mcp-server-elasticsearch-zx8086": {
                "command": "npx",
                "args": [
                    "@elastic/mcp-server-elasticsearch"
                ]
            }
        }
    }
}

McpServers

{
    "mcp-server-elasticsearch-zx8086": {
        "command": "npx",
        "args": [
            "@elastic/mcp-server-elasticsearch"
        ]
    }
}

License
Version
Bun

A production-ready Model Context Protocol (MCP) server that connects AI assistants like Claude Desktop to Elasticsearch clusters. This server provides comprehensive Elasticsearch operations through natural language interactions, featuring advanced configuration management, security controls, and extensive tooling.

This is an enhancement of the Official Elastic MCP Server with the four tools (Core Operations).

🚀 Key Features

- 🔧 Comprehensive Tooling: 60+ Elasticsearch operations including search, indexing, cluster management, and analytics
- ⚙️ Advanced Configuration: Type-safe configuration system with environment variable validation
- 🔒 Security Controls: Read-only mode with strict/warning options for safe production monitoring
- 📊 Rich Search: Advanced search with automatic highlighting, aggregations, and SQL support
- 🔄 Bulk Operations: Efficient bulk indexing, updating, and deletion with helper APIs
- 📈 Cluster Monitoring: Health checks, node statistics, and performance metrics
- 🛡️ Error Handling: Robust error handling with detailed logging and troubleshooting guides
- ⚡ Performance: Built on Bun runtime for optimal performance and modern JavaScript features

📋 Table of Contents

- Prerequisites
- Installation
- Quick Start
- Configuration
- Available Tools
- Usage Examples
- Development
- Architecture
- Security
- Troubleshooting

🔧 Prerequisites

Installing Bun

This project uses Bun as the JavaScript runtime for optimal performance. Install Bun using one of these methods:

macOS/Linux:

curl -fsSL https://bun.sh/install | bash

Windows (PowerShell):

irm bun.sh/install.ps1 | iex

Package Managers:
```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.