What is Elasticsearch7 Mcp Server

The elasticsearch7-mcp-server is an MCP server designed for Elasticsearch 7.x, providing a protocol interface for seamless interaction with Elasticsearch functionalities and ensuring compatibility with various versions of Elasticsearch 7.x.

Use cases

Use cases include performing basic and advanced searches in Elasticsearch indices, executing aggregation queries for data analysis, and integrating Elasticsearch functionalities into applications through MCP clients.

How to use

To use elasticsearch7-mcp-server, you can install it via Smithery or manually using pip. After installation, set the required environment variables and start the server. You can then connect to the server using any MCP client to perform operations such as pinging the server or executing search queries.

Key features

Key features include support for basic Elasticsearch operations, complete search functionality with aggregation queries, highlighting, sorting, and an easy-to-use MCP protocol interface for client interactions.

Where to use

Elasticsearch7-mcp-server can be used in various fields such as data analytics, application development, and any domain requiring advanced search capabilities and data retrieval from Elasticsearch.

Elasticsearch 7.x MCP Server

An MCP server for Elasticsearch 7.x, providing compatibility with Elasticsearch 7.x versions.

Features

• Provides an MCP protocol interface for interacting with Elasticsearch 7.x
• Supports basic Elasticsearch operations (ping, info, etc.)
• Supports complete search functionality, including aggregation queries, highlighting, sorting, and other advanced features
• Easily access Elasticsearch functionality through any MCP client

Requirements

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

Installation

Installing via Smithery

To install Elasticsearch 7.x MCP Server for Claude Desktop automatically via 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 9999

Using Docker Compose

1. Create a .env file and set ELASTIC_PASSWORD:

ELASTIC_PASSWORD=your_secure_password

2. Start the services:

docker-compose up -d

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

Using an MCP Client

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}

API Documentation

Currently supported MCP methods:

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

Search API Examples

Basic Search

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

Aggregation Query

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

Advanced Search

# Advanced search with highlighting, sorting, and filtering
advanced_response = client.call("es-search", {
    "index": "my_index",
    "query": {
        "bool": {
            "must": [
                {"match": {"content": "search term"}}
            ],
            "filter": [
                {"range": {"price": {"gte": 100, "lte": 200}}}
            ]
        }
    },
    "sort": [
        {"date": {"order": "desc"}},
        "_score"
    ],
    "highlight": {
        "fields": {
            "content": {}
        }
    },
    "_source": ["title", "date", "price"]
})

Development

1. Clone the repository
2. Install development dependencies
3. Run the server: elasticsearch7-mcp-server

License

[License in LICENSE file]

中文文档