Elasticsearch7 MCP Server

🚀 Elasticsearch 7.x MCP Server

A server providing MCP protocol interface for Elasticsearch 7.x, supporting compatibility with Elasticsearch 7.x versions.

🚀 Quick Start

This is a server that offers an MCP protocol interface for Elasticsearch 7.x, ensuring compatibility with the 7.x versions of Elasticsearch.

✨ Features

• Provide the MCP protocol interface for Elasticsearch 7.x.
• Support basic Elasticsearch operations (such as heartbeat detection, information query, etc.).
• Fully support search functions, including aggregation queries, highlighting, sorting, and other advanced features.
• Easily access Elasticsearch features through any MCP client.

📦 Installation

Automatic Installation via Smithery

Automatically install Elasticsearch 7.x MCP Server for the Claude desktop through Smithery:

npx -y @smithery/cli install @imlewc/elasticsearch7-mcp-server --client claude

Manual Installation

pip install -e .

Configuration Requirements

• Python 3.10+ or higher.
• Elasticsearch 7.x (version 7.17.x is recommended).

Environment Variable Configuration

The server requires the following environment variables:

• ELASTIC_HOST: The address of the Elasticsearch service (e.g., http://localhost:9200).
• ELASTIC_USERNAME: The username for Elasticsearch.
• ELASTIC_PASSWORD: The password for Elasticsearch.
• MCP_PORT: (Optional) The listening port of the MCP server, with a default of 9999.

Using Docker Compose

1. Create a .env file and set ELASTIC_PASSWORD:

ELASTIC_PASSWORD=your_secure_password

2. Start the service:

docker-compose up -d

This will start a three-node Elasticsearch 7.17.10 cluster, Kibana, and the MCP server.

💻 Usage Examples

Basic Usage

You can use any MCP client to connect to the MCP server:

from mcp import MCPClient

client = MCPClient("localhost:9999")
response = client.call("es-ping")
print(response)  # {"success": true}

Advanced Usage

Basic Search

response = client.call("es-search", body={
    "query": {
        "match_all": {}
    }
})
print(response)

Search with Filtering

response = client.call("es-search", body={
    "query": {
        "term": {
            "field": "value"
        }
    }
}, index="your_index_name")
print(response)

📚 Documentation

Environment Variable Explanation

• ELASTIC_HOST: Specify the address of the Elasticsearch service, with a default of localhost.
• ELASTIC_PORT: Specify the port of the Elasticsearch service, with a default of 9200.
• MCP_LISTEN: Specify the address that the MCP server listens on, with a default of 0.0.0.0.
• MCP_PORT: Specify the listening port of the MCP server, with a default of 9999.

Development Guide

1. Clone the repository:

git clone https://github.com/your-repository.git
cd your-repository

2. Install dependencies:

pip install -r requirements.txt

3. Start the server:

python server.py

📄 License

For license information, please refer to the LICENSE file.