How to Use the Grafana MCP in Pydantic AI

Build type-safe observability workflows using Pydantic AI to validate your Grafana metrics.

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 Pydantic AI

Create your Vinkius account to connect Grafana to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Force strict type safety on your Grafana metrics

Your Pydantic AI agent needs to act on accurate Grafana telemetry data without risking runtime crashes. By using this MCP Server's `firing_alerts` tool, Pydantic AI validates the alert schema before your model even processes it. If Grafana returns an unexpected alert payload structure, the Pydantic AI framework halts execution immediately. This prevents your agent from acting on corrupted or incomplete alert data.

Validate Grafana dashboard structures with this MCP Server

Parsing complex Grafana dashboard JSONs can easily break standard LLM parsers. Your Pydantic AI agent calls `get_dashboard` to pull panel configurations, validating the layout schema at runtime. It uses `search_dashboards` to find the exact Grafana dashboard UID safely. This structure ensures that only well-formed Grafana dashboard metadata reaches your Pydantic AI decision-making loops.

Check Grafana datasource configurations safely

Querying databases blindly is a massive risk for production systems. The agent calls `list_datasources` to get a validated list of active metrics backends in your Grafana environment. The Pydantic AI framework maps the Grafana response directly to type-safe Python models. This guarantees that your agent only interacts with valid, verified Grafana datasource types.

Setup guide

Set up Grafana MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "grafana-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Grafana tools.",
)

result = await agent.run("List recent Grafana transactions")
print(result.output)

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 Pydantic AI

Instantiate the MCPToolset helper with your Vinkius HTTP endpoint. Pass this object into the toolsets parameter of your Agent constructor.

The framework raises a validation error immediately. This loud failure prevents your agent from running hallucinated queries or misinterpreting system health.

Yes, the framework uses the unified toolset approach over SSE or streamable HTTP. Avoid the deprecated MCPServerHTTP class and use MCPToolset instead.

Yes, this toolset is model-agnostic. You can run your Grafana diagnostics using local models, Anthropic, or Gemini while maintaining strict validation.

Your Grafana datasource metadata and query structures are processed entirely in memory within ephemeral, zero-trust sandboxes. No telemetry data is ever persisted or used for training.

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