Elasticsearch

Elasticsearch MCP Server

Overview

A Model Context Protocol (MCP) server implementation that provides Elasticsearch interaction. This server enables searching documents, analyzing indices, and managing cluster through a set of tools.

Demo

https://github.com/user-attachments/assets/f7409e31-fac4-4321-9c94-b0ff2ea7ff15

Features

Index Operations

list_indices: List all indices in the Elasticsearch cluster.
get_mapping: Retrieve the mapping configuration for a specific index.
get_settings: Get the settings configuration for a specific index.

Document Operations

search_documents: Search documents in an index using Elasticsearch Query DSL.

Cluster Operations

get_cluster_health: Get health status of the cluster.
get_cluster_stats: Get statistical information about the cluster.

Start Elasticsearch Cluster

Start the Elasticsearch cluster using Docker Compose:

1docker-compose up -d

This will start a 3-node Elasticsearch cluster and Kibana. Default Elasticsearch username elastic, password test123.

You can access Kibana from http://localhost:5601.

Usage with Claude Desktop

Option 1: Installing via Smithery

To install Elasticsearch Server for Claude Desktop automatically via Smithery:

1npx -y @smithery/cli install elasticsearch-mcp-server --client claude

Option 2: Using uvx

Using uvx will automatically install the package from PyPI, no need to clone the repository locally. Add the following configuration to Claude Desktop's config file claude_desktop_config.json.

1{
2  "mcpServers": {
3    "elasticsearch-mcp-server": {
4      "command": "uvx",
5      "args": [
6        "elasticsearch-mcp-server"
7      ],
8      "env": {
9        "ELASTIC_HOST": "https://localhost:9200",
10        "ELASTIC_USERNAME": "elastic",
11        "ELASTIC_PASSWORD": "test123"
12      }
13    }
14  }
15}

Option 3: Using uv with local development

Using uv requires cloning the repository locally and specifying the path to the source code. Add the following configuration to Claude Desktop's config file claude_desktop_config.json.

1{
2  "mcpServers": {
3    "elasticsearch": {
4      "command": "uv",
5      "args": [
6        "--directory",
7        "path/to/src/elasticsearch_mcp_server",
8        "run",
9        "elasticsearch-mcp-server"
10      ],
11      "env": {
12        "ELASTIC_HOST": "https://localhost:9200",
13        "ELASTIC_USERNAME": "elastic",
14        "ELASTIC_PASSWORD": "test123"
15      }
16    }
17  }
18}

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

Restart Claude Desktop to load the new MCP server.

Now you can interact with your Elasticsearch cluster through Claude using natural language commands like:

"List all indices in the cluster"
"How old is the student Bob?"
"Show me the cluster health status"

License

This project is licensed under the Apache License Version 2.0 - see the LICENSE file for details.

Contents