Skip to main content
Glama

Elasticsearch MCP Server

by y0zg

Elasticsearch MCP Server

An AI-powered log analysis tool that connects Claude Desktop directly to your Elasticsearch cluster. Ask Claude questions about your logs in plain English and get intelligent insights.

What it does

Instead of writing complex Elasticsearch queries, just ask Claude things like:

  • "Show me all 5xx errors from the last hour"
  • "What's causing the slow database queries?"
  • "Find unique IPs hitting my API in the last 5 minutes"
  • "Is my Elasticsearch cluster healthy?"

Claude will search your logs, analyze patterns, and give you actionable insights.

Quick setup

1. Install dependencies

cd mcp-elasticsearch python3 -m venv venv source venv/bin/activate pip install -r requirements.txt

2. Build the extension

npm install -g @anthropic-ai/dxt dxt init # Use 'mcp-elasticsearch-server.py' as entry point dxt pack

3. Install in Claude Desktop

  • Double-click the generated mcp-elasticsearch.dxt file
  • Click "Install" when prompted
  • Restart Claude Desktop

That's it! Now you can chat with your logs.

Real examples

You: "Find unique public IPs for ingress traffic in the last 5 minutes"

Configuration

The extension connects to localhost:9200 by default. To change this, edit the ES_HOST in manifest.json:

"env": { "ES_HOST": "your-elasticsearch-host:9200" }

For secured clusters, you can add username/password through environment variables.

Requirements

  • Elasticsearch 7.x or 8.x (tested with v8)
  • Python 3.8+
  • Claude Desktop (latest version)
  • Node.js (for building the extension)

Troubleshooting

Extension won't install?

  • Make sure you have the latest Claude Desktop
  • Try removing old extensions first

Connection errors?

  • Check if Elasticsearch is running
  • Verify the host/port in your config

Still having issues?

# Test the connection manually source venv/bin/activate python -c "from elasticsearch import Elasticsearch; print('Connected:', Elasticsearch(['localhost:9200']).ping())"

What's included

The MCP server gives Claude these tools:

  • search_elasticsearch_logs - Basic log searching
  • analyze_error_patterns - Find and categorize errors
  • analyze_performance_issues - Detect slow operations
  • get_cluster_health - Monitor Elasticsearch health
  • analyze_index_performance - Optimize index performance

Time ranges

Use natural language for time ranges:

  • "last 5 minutes", "1 hour", "2 days", "1 week"
  • Or shortcuts like "5m", "1h", "2d", "1w"

License

MIT - use it however you want.


Ready to chat with your logs? Install the extension and start asking Claude questions about your Elasticsearch data!

-
security - not tested
F
license - not found
-
quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Enables Claude Desktop to connect directly to Elasticsearch clusters for intelligent log analysis through natural language queries. Users can ask questions about their logs in plain English and get actionable insights without writing complex Elasticsearch queries.

  1. What it does
    1. Quick setup
      1. 1. Install dependencies
      2. 2. Build the extension
      3. 3. Install in Claude Desktop
    2. Real examples
      1. Configuration
        1. Requirements
          1. Troubleshooting
            1. What's included
              1. Time ranges
                1. License

                  MCP directory API

                  We provide all the information about MCP servers via our MCP API.

                  curl -X GET 'https://glama.ai/api/mcp/v1/servers/y0zg/mcp-elasticsearch'

                  If you have feedback or need assistance with the MCP directory API, please join our Discord server