How to Use the New Relic MCP in Google ADK

Q: How do I set up the Google ADK to use the New Relic MCP Server?

It's straightforward. After installing google-adk, you create an McpToolset and point it to the Vinkius URL for this New Relic MCP Server. Then you just add that toolset to your LlmAgent's list of tools.

Q: Can I choose which New Relic functions are available to my agent?

You can. When you configure the McpToolset in your ADK code, there's an optional toolnames filter. This lets you expose only a specific subset of the New Relic tools, like runnrql and listalerts, to a particular agent.

Let your Google ADK agent query New Relic metrics via this MCP Server and correlate them with your Google Cloud data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect New Relic MCP to Google ADK

Create your Vinkius account to connect New Relic to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup New Relic with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run NRQL, Analyze in BigQuery

This is the bridge between your app's performance and your data warehouse. Your ADK agent can use the `run_nrql` tool to pull detailed performance metrics, error logs, or custom event data directly from New Relic's datastore. The real power comes next. Because you're in the Google ecosystem, the agent can take that data and push it into a BigQuery table. This lets you join New Relic observability data with business data, run large-scale analytics, and build reports in Looker Studio.

Connect New Relic to your Google ADK Agent with this MCP Server

Give your Gemini-powered agent a direct view into your infrastructure's health. It can use `list_entities` to get a full inventory of what New Relic is monitoring, then use `get_entity_details` to zoom in on specific hosts, services, or applications. This is especially useful for agents managing Google Cloud resources. An agent can detect a GKE pod issue, then immediately ask New Relic for the APM summary of the service running on it using `get_apm_summary`. It connects the infrastructure layer with the application layer.

Automate SLO and Alert Monitoring

You can build an agent that acts as a dedicated SRE. It uses `list_service_levels` to track SLO compliance and `list_alerts` to watch for active incidents across your stack. This frees up your team from constant dashboard-watching. When an alert fires, the agent can start its own investigation. It can check dependencies, look for recent deployments in your Google Cloud logs, and use the long-context window of Gemini to reason about the sequence of events. This MCP Server provides the raw data to fuel that analysis.

Setup guide

Set up New Relic MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with New Relic tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="New Relic_agent",
    model="gemini-2.0-flash",
    instruction="You have access to New Relic tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by New Relic. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect New Relic now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about New Relic MCP in Google ADK

It's straightforward. After installing `google-adk`, you create an `McpToolset` and point it to the Vinkius URL for this New Relic MCP Server. Then you just add that toolset to your `LlmAgent`'s list of tools.

Yes, that's a primary use case. If you have New Relic agents installed on your GCE, GKE, or App Engine services, your ADK agent can use this MCP connection to query all that performance data, check for alerts, and investigate issues directly.

It's the native integration with the rest of Google Cloud. Your agent can pull data from New Relic with `run_nrql` and then use other tools to cross-reference it with logs in Cloud Logging or datasets in BigQuery, all within a single agentic workflow.

You can. When you configure the `McpToolset` in your ADK code, there's an optional `tool_names` filter. This lets you expose only a specific subset of the New Relic tools, like `run_nrql` and `list_alerts`, to a particular agent.

The agent can access your account's observability data, including metrics, entity metadata, alerts, and dashboard configs. Security is handled by Vinkius's zero-trust platform. The connection is ephemeral, runs in a V8 sandbox, and uses a short-lived token so your New Relic API key is never exposed.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript