mcp_newrelic
Documentation

New Relic MCP Server
A Model Context Protocol (MCP) server for querying New Relic logs using NRQL queries. This server enables Large Language Models (LLMs) like Claude to interact with your New Relic data.
> Claude Code users: Also available as an installable plugin with slash commands, skills, and an investigation agent — no MCP server needed.
> Install with: `/plugin marketplace add Ivlad003/plugins` then `/plugin install newrelic-observability@ivlad-plugins`
> See Ivlad003/plugins for details.
Features
- Query New Relic logs and metrics using NRQL
- Detailed error logging
- Easy integration with Claude Desktop
- Human-readable output formatting
- Configurable New Relic account ID
Setup Instructions
Prerequisites
- Python 3.10 or higher
- New Relic account and API key
- Claude Desktop application
Installation Steps
1. Install `uv` package manager:
# On macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
# On Windows (PowerShell)
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"2. Create and setup project:
# Create directory
mkdir newrelic-mcp
cd newrelic-mcp
# Create virtual environment
uv venv
# Activate virtual environment
source .venv/bin/activate # On Unix/macOS
.venv\Scripts\activate # On Windows
# Install dependencies
uv pip install "mcp[cli]" httpx3. Create server file `newrelic_logs_server.py` with the provided code.
4. Configure your environment variables:
# On Unix/macOS
export NEW_RELIC_API_KEY="your-api-key-here"
export NEW_RELIC_ACCOUNT_ID="your-account-id-here"
# On Windows (CMD)
set NEW_RELIC_API_KEY=your-api-key-here
set NEW_RELIC_ACCOUNT_ID=your-account-id-here
# On Windows (PowerShell)
$env:NEW_RELIC_API_KEY = "your-api-key-here"
$env:NEW_RELIC_ACCOUNT_ID = "your-account-id-here"Claude Desktop Integration
Configure Claude Desktop by editing your configuration file:
- macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
- Windows: `%APPDATA%\Claude\claude_desktop_config.json`
Add the following configuration:
{
"mcpServers": {
"newrelic": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/newrelic-mcp",
"run",
"app.py"
],
"env": {
"NEW_RELIC_API_KEY": "your-api-key-here",
"NEW_RELIC_ACCOUNT_ID": "your-account-id-here"
}
}
}
}Usage
Example NRQL Queries
1. Basic Transaction Query:
SELECT * FROM Transaction SINCE 1 hour ago2. Error Analysis:
SELECT * FROM Transaction WHERE error IS TRUE SINCE 1 hour ago LIMIT 103. Performance Analysis:
SELECT average(duration) FROM Transaction FACET name ORDER BY average(duration) DESC LIMIT 5Example Claude Prompts
You can ask Claude questions like:
- "Show me all transactions from the last hour"
- "Are there any errors in our application?"
- "What are our slowest endpoints?"
Debugging
Viewing Logs
# On macOS/Linux
tail -f ~/Library/Logs/Claude/mcp-server-newrelic.log
# On Windows
type %APPDATA%\Claude\logs\mcp-server-newrelic.logTesting with MCP Inspector
Test your server functionality using:
npx @modelcontextprotocol/inspector uv run newrelic_logs_server.pyCommon Issues
1. Authentication Errors:
- Check if NEW_RELIC_API_KEY is set correctly
- Verify API key has correct permissions
- Ensure API key is valid
2. Query Errors:
- Verify NRQL syntax
- Check account ID in code matches your account
- Ensure queried data exists in the time range
3. Connection Issues:
- Check network connectivity
- Verify GraphQL endpoint is accessible
- Ensure no firewalls are blocking connections
Security Notes
- Never commit API keys to version control
- Use environment variables for sensitive data
- Keep dependencies updated
- Monitor query patterns and access logs
Development
Local Testing
1. Set environment variables:
export NEW_RELIC_API_KEY="your-api-key-here"
export NEW_RELIC_ACCOUNT_ID="your-account-id-here"2. Run the server:
uv run newrelic_logs_server.pyCode Structure
The server implements:
- Single NRQL query tool
- Configurable New Relic account ID
- Comprehensive error handling
- Detailed logging
- Response formatting
Testing Changes
1. Modify code as needed
2. Test with MCP Inspector
3. Restart Claude Desktop to apply changes
Troubleshooting Guide
1. Server Not Starting:
- Check Python version
- Verify all dependencies are installed
- Ensure virtual environment is activated
2. Query Not Working:
- Check logs for detailed error messages
- Verify NRQL syntax
- Ensure data exists in queried time range
3. Claude Not Connecting:
- Verify configuration file syntax
- Check paths are absolute
- Restart Claude Desktop
Contributing
1. Fork the repository
2. Create a feature branch
3. Submit a pull request
License
This project is licensed under the MIT License.
Support
If you encounter issues:
1. Check the logs
2. Review common issues section
3. Test with MCP Inspector
4. File an issue on GitHub
Frequently asked questions
What is mcp_newrelic?
mcp_newrelic is a Model Context Protocol (MCP) server listed in the TrackMCP directory.
How do I install mcp_newrelic?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp_newrelic open source?
Yes — it is hosted on GitHub at https://github.com/Ivlad003/mcp_newrelic and has 26 stars.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Python SQL Parser and Transpiler
MCP server that interacts with Obsidian via the Obsidian rest API community plugin
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP