Elastic Semantic Search MCP Server

🚀 MCP Server: Elasticsearch Semantic Search Tool

This demo repository is for: https://j.blaszyk.me/tech-blog/mcp-server-elasticsearch-semantic-search/

Table of Contents

• Overview
• Running the MCP Server
• Integrating with Claude Desktop
• Crawling Search Labs Blog Posts
  • 1. Verify Crawler Settings
  • 2. Configure Elasticsearch
  • 3. Update Index Mapping for Semantic Search
  • 4. Start Crawling
  • 5. Verify Indexed Documents

Overview

This repository provides a Python implementation of the MCP Server for performing semantic search in Elasticsearch using Search Labs blog posts.

It assumes that you have crawled the blog posts and stored them in the search-labs-posts index created by the Elastic Open Crawler.

🚀 Quick Start

Running the MCP Server

Add ES_URL and ES_AP_KEY to the .env file. (See here to generate an API key with minimal permissions.)

Start the server in the MCP Monitor:

make dev

After running, access the MCP Monitor: http://localhost:5173

Integrating with Claude Desktop

To add the MCP Server to Claude Desktop:

make install-claude-config

This updates the claude_desktop_config.json file in your home directory. The Claude application will automatically detect and connect to this configuration on the next restart.

Crawling Search Labs Blog Posts

1. Verify Crawler Settings

Ensure that all necessary dependencies are installed and the environment variables are correctly configured. Run the following command to verify that the crawler is working properly:

python crawler.py --test

2. Configure Elasticsearch

In the elasticsearch.yml file, update the following configuration to optimize performance and index management:

# Elasticsearch configuration
cluster.name: "search-labs-cluster"
node.name: "crawler-node"
path.data: /var/lib/elasticsearch

3. Update Index Mapping for Semantic Search

Create a new file index-mapping.json and add the following content to define fields and analyzers:

{
  "mappings": {
    "properties": {
      "title": {"type": "text", "analyzer": "standard"},
      "content": {"type": "text", "analyzer": "standard"},
      "date": {"type": "date", "format": "yyyy-MM-dd"}
    }
  }
}

4. Start Crawling

Run the following command to start the crawler:

make start-crawler

To stop the crawler, press Ctrl+C.

5. Verify Indexed Documents

Use the Elasticsearch query tool to verify the data in the index:

curl -X GET "http://localhost:9200/search-labs-posts/_search?pretty"

⚠️ Important Note

• Ensure that the Elasticsearch service is running.
• Regularly update the crawler rules to adapt to changes in the Search Labs page structure.
• In a production environment, it is recommended to configure logging and error handling mechanisms.

If you have any questions, please refer to the project documentation or contact the maintainers.