o11y-mcp-server

o11y-mcp-server

Connects to Elastic Agent Builder to enable AI-powered application health monitoring using OTEL metrics, traces, and logs from Elastic Serverless Observability.

Category
Visit Server

README

🤖 Elastic Agent Builder Integration

Connect to Elastic Agent Builder for AI-powered application health monitoring using OTEL data from Elastic Serverless Observability.

✨ Features

  • AI-Powered Analysis through Elastic Agent Builder
  • Real-time Insights from OTEL metrics, traces, and logs
  • Built-in Tools for comprehensive monitoring
  • Easy Integration with Cursor IDE and other MCP clients
  • No Local Server Required - direct connection to Elastic

🎯 Available Agent Builder Tools

  • platform.core.search - Search OTEL data in Elasticsearch
  • platform.core.execute_esql - Execute ESQL queries on OTEL data
  • platform.core.generate_esql - Generate ESQL queries for analysis
  • Built-in Analysis - Error patterns, performance metrics, resource utilization
  • Real-time Monitoring - Application health, service dependencies, bottlenecks

🚀 Quick Start

Prerequisites

  • Elastic Serverless Observability endpoint with Agent Builder enabled
  • Valid API key for Elastic
  • Cursor IDE (optional, for MCP integration)

Installation

  1. Clone the repository

    git clone git@github.com:poulsbopete/o11y-mcp-server.git
    cd o11y-mcp-server
    
  2. Configure credentials

    # Option 1: Use setup script (recommended)
    ./setup-env.sh
    # Then edit .env file with your credentials
    
    # Option 2: Set environment variables
    export ELASTIC_ENDPOINT=https://your-endpoint.kb.us-east-1.aws.elastic.cloud
    export ELASTIC_API_KEY=your-api-key
    
  3. Connect to Agent Builder

    # Test Agent Builder connection
    ./connect-to-agent-builder.sh
    
    # Query application health
    ./query-application-health.sh
    
  4. Set up Cursor integration (optional)

    # Create Cursor MCP configuration
    ./setup-cursor-agent-builder.sh
    

🔗 Cursor Integration

Quick Setup

./setup-cursor-agent-builder.sh

Manual Setup

  1. Run the Cursor configuration script
  2. Restart Cursor IDE
  3. Connect to Elastic Agent Builder
  4. Ask questions like "What's the health of my applications?"

📊 Data Sources

Agent Builder connects to Elastic Serverless Observability and analyzes:

  • Metrics: metrics-* indices (CPU, memory, custom metrics)
  • Logs: logs-* indices (application logs, errors, events)
  • Traces: traces-* indices (distributed tracing data)

🛠️ Configuration

Environment Variables

  • ELASTIC_ENDPOINT - Your Elastic Serverless endpoint
  • ELASTIC_API_KEY - Your Elastic API key
  • LOG_LEVEL - Logging level (default: INFO)

Cursor MCP Configuration

The setup script creates ~/.cursor/mcp_config.json with Agent Builder integration.

📝 Example Queries

Once connected to Agent Builder, you can ask:

  • "What's the overall health of my applications?"
  • "Show me metrics for the payment service"
  • "What errors are happening in the last hour?"
  • "Find the slowest operations in my system"
  • "Analyze resource utilization across all services"
  • "Show me trace analysis for the checkout flow"
  • "Generate an ESQL query for error analysis"

🔧 Troubleshooting

Agent Builder Connection Issues

  • Verify Elastic endpoint and API key
  • Check if Agent Builder is enabled on your Elastic instance
  • Test connection: ./connect-to-agent-builder.sh

No Data Found

  • Check if applications are sending OTEL data
  • Verify time range includes recent data
  • Ensure proper Elastic cluster configuration

Cursor Integration Issues

  • Verify MCP configuration in Cursor settings
  • Check Agent Builder is accessible
  • Restart Cursor after configuration changes

📚 Documentation

  • CURSOR-MCP-INTEGRATION.md - Cursor integration guide
  • connect-to-agent-builder.sh - Agent Builder connection script
  • query-application-health.sh - Application health analysis script

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature-name
  3. Commit changes: git commit -am 'Add feature'
  4. Push to branch: git push origin feature-name
  5. Submit a pull request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments


Ready to monitor your application health with AI-powered insights through Elastic Agent Builder! 🎉

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured