Imlewc Elasticsearch7 MCP Server

🚀 Elasticsearch 7.x MCP Server

A server that provides MCP protocol interfaces for Elasticsearch 7.x, supporting compatibility with Elasticsearch 7.x versions.

✨ Features

• Provide MCP protocol access interfaces 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.
• Enable easy access to Elasticsearch functions through any MCP client.

📦 Dependencies

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

📦 Installation

Automatic Installation via Smithery

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

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

Manual Installation

pip install -e .

💻 Environment Variables

The server requires the following environment variables:

• ELASTIC_HOST: Elasticsearch host address (e.g., http://localhost:9200).
• ELASTIC_USERNAME: Elasticsearch username.
• ELASTIC_PASSWORD: Elasticsearch password.
• MCP_PORT: (Optional) MCP server listening port, default is 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

# Basic search
search_response = client.call("es-search", {
    "index": "my_index",
    "query": {
        "match": {
            "title": "search keyword"
        }
    },
    "size": 10,
    "from": 0
})

Aggregation Query

# Aggregation query
agg_response = client.call("es-search", {
    "index": "my_index",
    "size": 0,  # Only need aggregation results, no document content
    "aggs": {
        "categories": {
            "terms": {
                "field": "category.keyword",
                "size": 10
            }
        },
        "avg_price": {
            "avg": {
                "field": "price"
            }
        }
    }
})

Advanced Search

# Advanced search with highlighting and sorting
search_response = client.call("es-search", {
    "index": "my_index",
    "query": {
        "multi_match": {
            "query": "search keyword",
            "fields": ["title", "content"]
        }
    },
    "highlight": {
        "pre_tag": "<em>",
        "post_tag": "</em>",
        "fields": {
            "title": {},
            "content": {}
        }
    },
    "sort": [
        {"price": { "order": "asc" }}
    ]
})

📚 Documentation

API Documentation

Currently supported MCP methods:

• es-ping: Check the Elasticsearch connection status.
• es-info: Get Elasticsearch cluster information.
• es-search: Search for documents in the Elasticsearch index.

🔧 Development

Run the following command in the project root directory to start the server:

python -m elasticsearch_mcp_server

By default, the server will start at http://localhost:9999.

📄 License

This project is licensed under the MIT License.