mcpField
N
nr-mcp: New Relic MCP Server

nr-mcp: New Relic MCP Server

Local
github.com/ducduyn31Data & Analytics10Updated 75w ago

About nr-mcp: New Relic MCP Server

nr-mcp connects AI assistants to New Relic for incident debugging queries. It requires a New Relic account, API key, account ID, and region.

Key features

  1. 01Query New Relic for debugging incidents
  2. 02Connect through an MCP client
  3. 03Test tools with MCP Inspector

Use cases

  1. 01Investigate an incident using New Relic data
  2. 02Connect an AI assistant to a New Relic account
  3. 03Test tool calls and inspect responses

MCP support

The server provides New Relic querying capabilities to MCP clients. The README describes Docker-based client configuration and Stdio testing with MCP Inspector.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"nr": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"\\"
]
}
}
}
Run commanddocker run -i --rm '\'

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
oci\

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

nr-mcp: New Relic MCP Server

MCP server allowing AI agents to query New Relic for debugging incidents.


For Users

This section is for users who want to use the nr-mcp server with their AI assistants.

For detailed information on available tools and resources, see the Documentation section.

Prerequisites

  • New Relic account with:
    • API key
    • Account ID
    • Region (US or EU)

Quick Start

To connect an AI assistant to nr-mcp, add the following configuration to your MCP client setup:

Docker Connection
{
  "mcpServers": {
    "newrelic": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "NEW_RELIC_API_KEY",
        "-e",
        "NEW_RELIC_ACCOUNT_ID",
        "-e",
        "NEW_RELIC_REGION",
        "danielng123/nr-mcp:latest"
      ],
      "env": {
        "NEW_RELIC_API_KEY": "<YOUR_API_KEY>",
        "NEW_RELIC_ACCOUNT_ID": "<YOUR_ACCOUNT_ID>",
        "NEW_RELIC_REGION": "US"
      }
    }
  }
}

For Developers

This section is for developers who want to contribute to the nr-mcp project.

Development Setup

# Clone the repository
git clone https://github.com/ducduyn31/nr-mcp.git
cd nr-mcp

# Install dependencies
pnpm install

# Build the project
pnpm build

The MCP Inspector is a powerful tool for debugging and testing MCP servers and clients. We've added a streamlined development workflow that automatically watches for file changes, rebuilds the project, and runs the inspector:

# Start the development workflow
pnpm dev

This command:

  1. Watches the src directory for changes to .ts files
  2. Automatically rebuilds the project when changes are detected
  3. Runs the MCP Inspector in parallel
Manual Testing

You can also run these commands separately:

# Watch for file changes and rebuild
pnpm watch

# Start the inspector
pnpm inspector
Using the Inspector

Once the inspector is running:

  1. Open the web interface (typically at http://localhost:5173)
  2. Select "Connect to Server"
  3. Choose "Stdio" as the transport type
  4. Enter the command to start your server: node dist/index.js
  5. Click "Connect"

After connecting, you can:

  • Browse available tools
  • Make test calls with custom parameters
  • View responses and any errors
  • Record and replay testing sessions
Debugging Tips
  • Use the inspector to compare expected vs. actual responses
  • Monitor the full request/response cycle for each tool call
  • Check for proper error handling by intentionally sending invalid inputs
  • Verify that your tools adhere to their declared schemas

Development

# Create a new tool
pnpm create-tool

# Lint code
pnpm lint

# Format code
pnpm format

License

MIT


Documentation

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.