New Relic

New Relic is an MCP server that connects Model Context Protocol clients directly to New Relic observability platforms. Built with Python, it allows developers, DevOps engineers, and site reliability teams to execute New Relic Query Language (NRQL) statements through natural language requests inside AI clients like Claude Desktop. Instead of navigating the New Relic web interface to construct queries manually, users can inspect application logs, examine transaction records, diagnose application errors, and measure endpoint latency through conversational workflows. The server communicates with New Relic GraphQL APIs using an account ID and user API key, parses the resulting telemetry, and delivers human-readable output back to the connected client. It includes structured error handling and local logging to assist in troubleshooting query syntax issues or authentication problems. By bridging LLMs with telemetry datasets, the server allows engineers to conduct operational investigations and triage production incidents directly within their preferred workspace.

Category: Data & Analytics

Tags: logs, monitoring, new relic, nrql, telemetry

Visit New Relic

How to install and configure New Relic

1. Install the uv package manager and initialize a project directory: bash mkdir newrelic-mcp cd newrelic-mcp uv venv source .venv/bin/activate uv pip install "mcp[cli]" httpx 2. Set up your server script (app.py or newrelic_logs_server.py) and export your environment variables: bash export NEW_RELIC_API_KEY="your-api-key-here" export NEW_RELIC_ACCOUNT_ID="your-account-id-here" 3. Add the server to your Claude Desktop configuration file (claude_desktop_config.json): json { "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" } } } } 4. Restart Claude Desktop to load the server.

What you can do with New Relic

• Investigating production errors by running NRQL queries to pull failing transactions from recent service logs. - Analyzing API performance by querying average durations across application endpoints to identify latency bottlenecks. - Monitoring operational volume by fetching transaction counts and error rates across specified time windows. - Troubleshooting incidents conversationally using Claude to generate and execute targeted New Relic queries.

Key facts

• https://github.com/Ivlad003/mcp_newrelic
• Data & Analytics, Monitoring & Observability
• logs, monitoring, new relic, nrql, telemetry

Part of MCP Servers

What can New Relic MCP Server do?

The server enables LLMs to query New Relic telemetry data using NRQL. It formats query responses into readable text, handles error logging, and retrieves transaction data, error traces, and performance metrics directly into conversational workflows.

How do I install New Relic MCP Server?

Install Python 3.10 or higher and the uv package manager. Set up a project folder, install mcp[cli] and httpx, and register the server command inside your Claude Desktop configuration file with your New Relic credentials.

Which MCP clients work with New Relic MCP Server?

The server works with Claude Desktop on macOS and Windows, as well as developer tools like the MCP Inspector. Claude Code users can also install an observability plugin directly through their plugin marketplace.

Is New Relic MCP Server open source?

Yes, New Relic MCP Server is an open-source project released under the MIT License on GitHub.