How to Use the New Relic MCP in CrewAI

Deploy a specialized crew of autonomous SRE agents to monitor your stack using CrewAI and this MCP server.

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 CrewAI

Create your Vinkius account to connect New Relic to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Segment monitoring tasks across CrewAI

Handing one script twenty different monitoring tasks guarantees failure. You need dedicated workers handling specific parts of your infrastructure. Create a Tier 1 Support agent that constantly polls `list_alerts` and `list_entities`. When it finds an issue, it hands the context to a Senior SRE agent that runs complex `run_nrql` queries to diagnose the root cause.

Maintain state across diagnostic runs

Complex outages span multiple services and dashboards. An isolated script forgets what it saw three steps ago, but a crew shares everything it finds. The researcher agent pulls `get_apm_summary` data and stores it in the shared session memory. The reporting agent reads that exact data later to format a Slack update, never needing to call `list_service_levels` twice for the same information.

Restrict tool access by role

You cannot trust every autonomous worker with full access to your NerdGraph MCP Server endpoints. Some tasks just require basic visibility without deep query capabilities. Using the `tool_filter` parameter in `MCPServerHTTP`, you restrict your reporting agent to only use `list_dashboards` and `get_dashboard`. The deep diagnostic tools stay locked away with the senior agents.

Setup guide

Set up New Relic MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke New Relic tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="New Relic Analyst",
    goal="Access and analyze New Relic data via MCP.",
    backstory="Expert analyst with direct New Relic access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent New Relic transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="New Relic Analyst",
        goal="Access and analyze New Relic data via MCP.",
        backstory="Expert analyst with direct New Relic access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent New Relic transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Just drop the Vinkius URL into the mcps array when defining your agent. The framework automatically fetches the available endpoints and makes them ready for use.

They operate sequentially or hierarchically depending on your setup. A manager agent can delegate query tasks to multiple workers, but they will execute their specific MCP tool calls in order.

You can use stdio, SSE, or Streamable HTTP. For our managed endpoints, Streamable HTTP provides the most reliable connection for heavy telemetry pulls.

Import MCPServerHTTP from the core library. Pass a filter array to explicitly allow only the specific read operations you want that agent to touch.

Only the specific agent assigned to the task reads your configurations. The execution happens inside a temporary V8 sandbox that shreds your NerdGraph API responses the moment the session terminates.

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