New Relic MCP Server
Allows querying New Relic logs and metrics using NRQL queries, providing access to transaction data, error analysis, and performance metrics from a New Relic account.
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., "@New Relic MCP Servershow me errors in our application from the last 2 hours"
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.
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/pluginsthen/plugin install newrelic-observability@ivlad-pluginsSee 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
Related MCP server: Datadog MCP Server
Setup Instructions
Prerequisites
Python 3.10 or higher
New Relic account and API key
Claude Desktop application
Installation Steps
Install
uvpackage 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"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]" httpxCreate server file
newrelic_logs_server.pywith the provided code.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.jsonWindows:
%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
Basic Transaction Query:
SELECT * FROM Transaction SINCE 1 hour agoError Analysis:
SELECT * FROM Transaction WHERE error IS TRUE SINCE 1 hour ago LIMIT 10Performance 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
Authentication Errors:
Check if NEW_RELIC_API_KEY is set correctly
Verify API key has correct permissions
Ensure API key is valid
Query Errors:
Verify NRQL syntax
Check account ID in code matches your account
Ensure queried data exists in the time range
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
Set environment variables:
export NEW_RELIC_API_KEY="your-api-key-here"
export NEW_RELIC_ACCOUNT_ID="your-account-id-here"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
Modify code as needed
Test with MCP Inspector
Restart Claude Desktop to apply changes
Troubleshooting Guide
Server Not Starting:
Check Python version
Verify all dependencies are installed
Ensure virtual environment is activated
Query Not Working:
Check logs for detailed error messages
Verify NRQL syntax
Ensure data exists in queried time range
Claude Not Connecting:
Verify configuration file syntax
Check paths are absolute
Restart Claude Desktop
Contributing
Fork the repository
Create a feature branch
Submit a pull request
License
This project is licensed under the MIT License.
Support
If you encounter issues:
Check the logs
Review common issues section
Test with MCP Inspector
File an issue on GitHub
Available Tools
1 toolquery_logsB
Query New Relic logs using NRQL.
Args: query: NRQL query string (e.g., "SELECT * FROM Transaction") account_id: New Relic account ID (default from env var)
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| account_id | No | 1234567 |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and largely drops it. It never states that this is a read-only operation, whether results are limited or paginated, what time range NRQL defaults to, or what auth/scope is required for the account.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Short and front-loaded with the core action in the first sentence, followed by a compact arg list. The docstring-style 'Args:' block is a bit ceremonial but each line carries parameter information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter query tool with no output schema and no annotations, the description covers the parameters adequately but omits result shape, row/result limits, and pagination behavior. It is minimally viable rather than complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate, and it does: 'query' is explained as an NRQL string with a concrete example, and 'account_id' is described as taking a default from an environment variable. This is meaningful context the bare schema lacks, though the example query targets 'Transaction' rather than a log table, which is slightly off for a log tool.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource ('Query New Relic logs using NRQL'), which is unambiguous about what the tool does. There are no sibling tools to differentiate from, so 5 is not reachable, but the purpose itself is crisp.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It says the tool uses NRQL but gives no guidance on when to use it versus other retrieval tools, no prerequisites, and no exclusions. An agent gets the mechanism but not the selection criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
query_logs
TDQS
Scored across 1 tool
With only one tool, there is no possibility of overlap or misselection; its purpose (querying logs via NRQL) is unambiguous.
The single name query_logs follows a clean verb_noun snake_case convention that would scale predictably if more tools were added.
One tool is far too few for a platform like New Relic, which spans logs, metrics, APM, alerts, and dashboards; the surface feels like a stub rather than a server.
Only log querying is exposed, with no metric queries, APM data, alert/incident retrieval, or account/resource listing, leaving major observability workflows unreachable.
Maintenance
Related MCP Connectors
A Model Context Protocol server for Wix AI tools
Access New Relic observability data through MCP - query metrics, logs, traces, entities, and more
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Enable secure connectivity between Sentry issues and debugging data, and LLM clients, using a Model Context Protocol (MCP) server.
Related MCP Servers
- FlicenseCqualityDmaintenanceA Model Context Protocol server that enables searching and retrieving information from DevRev using its APIs with Claude.23-
- AlicenseBqualityNot gradedmaintenanceA Model Context Protocol server that enables AI assistants to interact with Datadog's observability platform through natural language.72MIT
- AlicenseBqualityCmaintenanceEnables natural language access to New Relic for monitoring, querying, and managing dashboards, entities, alerts, and deployments via the Model Context Protocol.529MIT
- FlicenseCqualityDmaintenanceMCP server allowing AI agents to query New Relic for debugging incidents.2-