o11y-mcp-server
Provides tools to connect to Elastic Agent Builder for AI-powered application health monitoring using OTEL data from Elastic Serverless Observability.
Allows searching OTEL data in Elasticsearch indices (metrics, logs, traces) and executing ESQL queries for analysis.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@o11y-mcp-serverWhat's the health of my payment service?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🤖 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
Related MCP server: otel-mcp-server
🎯 Available Agent Builder Tools
platform.core.search- Search OTEL data in Elasticsearchplatform.core.execute_esql- Execute ESQL queries on OTEL dataplatform.core.generate_esql- Generate ESQL queries for analysisBuilt-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
Clone the repository
git clone git@github.com:poulsbopete/o11y-mcp-server.git cd o11y-mcp-serverConfigure 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-keyConnect to Agent Builder
# Test Agent Builder connection ./connect-to-agent-builder.sh # Query application health ./query-application-health.shSet up Cursor integration (optional)
# Create Cursor MCP configuration ./setup-cursor-agent-builder.sh
🔗 Cursor Integration
Quick Setup
./setup-cursor-agent-builder.shManual Setup
Run the Cursor configuration script
Restart Cursor IDE
Connect to Elastic Agent Builder
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 endpointELASTIC_API_KEY- Your Elastic API keyLOG_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 guideconnect-to-agent-builder.sh- Agent Builder connection scriptquery-application-health.sh- Application health analysis script
🤝 Contributing
Fork the repository
Create a feature branch:
git checkout -b feature-nameCommit changes:
git commit -am 'Add feature'Push to branch:
git push origin feature-nameSubmit a pull request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
Built with Elastic Agent Builder
Integrates with Elastic Serverless Observability
Compatible with Cursor IDE
Ready to monitor your application health with AI-powered insights through Elastic Agent Builder! 🎉
This server cannot be deployed
Maintenance
Related MCP Connectors
LLM Orchestration Agent (Opentelemetry Api)
Connect AI agents to CloudBees Unify: feature flags, CI/CD, release orchestration, and security
Build and supervise fleets of agents from Claude Code, Codex or Cursor. Connects over OAuth.
Connect, monitor, and control AI agents — tasks, approvals, schedules, and governance.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables LLMs to query telemetry data via the Spyglass AI agent, providing intelligent insights about application performance, errors, and bottlenecks.1MIT
- AlicenseNot gradedqualityDmaintenanceEnables natural language querying and analysis of OpenTelemetry traces, metrics, and logs stored in Elasticsearch/OpenSearch, allowing AI assistants to investigate performance issues, find root causes, and explore system behavior.12 npm14MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to search Elasticsearch logs, retrieve log details, analyze service health, scan local codebases for APIs, and create Kibana dashboards.510 npmMIT
- AlicenseNot gradedqualityAmaintenanceConnects AI assistants to New Relic with read-only access to NRQL, logs, metrics, traces, alerts, and more. Offers optional, gated write operations with a dry-run and confirmation workflow.34 npmApache 2.0