How to Use the Grafana MCP in OpenAI Agents SDK

Q: Can I route firing alerts to specific agents?

You can use native SDK handoffs. Have a triage agent run firingalerts, inspect the labels, and route the payload to a dedicated database or network agent.

Get instant production-grade Grafana alert triage and dashboard checks inside your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Grafana MCP to OpenAI Agents SDK

Create your Vinkius account to connect Grafana to OpenAI Agents SDK 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 Grafana with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Triage Grafana outages with OpenAI Agents SDK

Your OpenAI Agents SDK agent monitors live infrastructure issues by checking Grafana alert states directly. By invoking this MCP Server's `firing_alerts` tool, the agent grabs active alerts with their exact labels and annotations to diagnose failures. This setup lets you build autonomous SRE loops inside your OpenAI Agents SDK workflow. The agent uses the Grafana alert data to figure out which microservice is failing, then hands off the task to a specialized mitigation agent.

Inspect Grafana telemetry configurations in real time

When a Grafana alert fires, your OpenAI Agents SDK agent needs to see the exact queries driving the visualization. It calls `search_dashboards` to find the right metrics view, then pulls the exact configuration using the `get_dashboard` tool. This exposes the underlying Grafana Prometheus or SQL queries directly to your OpenAI model. It bypasses the need for manual console digging during high-pressure incidents.

Map Grafana data infrastructure via this MCP Server

Understanding your Grafana telemetry footprint is critical for automated OpenAI Agents SDK troubleshooting. The agent calls `list_datasources` to map out every connected database and metrics store. This prevents the OpenAI agent from guessing where to run diagnostics. It knows exactly which Grafana Prometheus instances or database clusters are available for deep-dive checks.

Setup guide

Set up Grafana MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Grafana tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Grafana tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Grafana tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Grafana Agent",
            instructions="You have access to Grafana tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Grafana. 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 Grafana 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 Grafana MCP in OpenAI Agents SDK

Install the package using pip, then initialize the server streamable HTTP class with your Vinkius endpoint. Pass this instance directly into your Agent constructor using the server list parameter.

Yes, the SDK handles discovery automatically. When you pass the server context to your agent, it exposes `list_datasources` and `search_dashboards` immediately without manual schema definitions.

You should enable the tool cache option in your SDK config to prevent redundant hits. This limits calls to `get_dashboard` when your agent is actively analyzing a single panel configuration.

You can use native SDK handoffs. Have a triage agent run `firing_alerts`, inspect the labels, and route the payload to a dedicated database or network agent.

No, your Grafana dashboard JSON configurations and alert payloads stay within the Vinkius secure sandbox. The connection uses your private endpoint token, meaning raw metrics metadata never leaks to public logs.

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