How to Use the Grafana MCP in LangChain

Q: Can a LangChain agent modify my dashboards using this MCP Server?

No. This server only exposes read-only tools like getdashboard and searchdashboards. Your LangChain agent can read configurations to diagnose issues, but it cannot alter or delete your production visualization setups.

Q: Does LangSmith trace the Grafana tool calls made by LangChain?

Yes, every call to listdatasources or firingalerts is fully traced in LangSmith. You can inspect the exact payload, latency, and token cost of each Grafana tool execution within your agentic run.

Q: How does LangChain find the right Grafana dashboard to inspect?

The agent runs searchdashboards with a specific service name or tag. Once it gets the unique identifier, it passes that ID to getdashboard to inspect the underlying panels and metrics.

Run LangChain reasoning chains that pull live telemetry from Grafana to catch and fix production issues fast.

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 LangChain

Create your Vinkius account to connect Grafana to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map out active incidents using LangChain chains

Your LangChain agent can run recursive diagnostic loops when production breaks. By combining the `firing_alerts` tool with LangSmith tracing, you see exactly which Grafana alert triggered and how your chain responded. The LangChain agent parses the alert labels and decides whether to fetch more context. It feeds those labels directly into the next step of your chain to narrow down the blast radius in Grafana.

Inspect live dashboard configurations in LangChain

This MCP Server lets your LangChain agent pull down complete panel queries using `get_dashboard`. Instead of guessing what metrics a Grafana dashboard tracks, the agent reads the raw JSON to check database load. You can feed this Grafana dashboard configuration directly into LangChain's structured output parsers. The agent extracts target thresholds and compares them against live telemetry to spot silent failures.

Track down data sources across your infrastructure

When an alert fires, your LangChain agent needs to know where to query. It uses `list_datasources` to find configured Grafana backends, then matches them against the targets found via `search_dashboards`. This turns static runbooks into dynamic LangChain pipelines. The agent discovers the correct Grafana database endpoint on the fly, keeping your SRE chain flexible.

Setup guide

Set up Grafana MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Grafana tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "grafana-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Grafana transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You should configure LangChain's built-in retry logic with exponential backoff. The agent can query `firing_alerts` frequently, but caching dashboard JSON locally prevents hitting Grafana rate limits during a major outage storm.

No. This server only exposes read-only tools like `get_dashboard` and `search_dashboards`. Your LangChain agent can read configurations to diagnose issues, but it cannot alter or delete your production visualization setups.

Yes, every call to `list_datasources` or `firing_alerts` is fully traced in LangSmith. You can inspect the exact payload, latency, and token cost of each Grafana tool execution within your agentic run.

The agent runs `search_dashboards` with a specific service name or tag. Once it gets the unique identifier, it passes that ID to `get_dashboard` to inspect the underlying panels and metrics.

Your Grafana API tokens are kept inside Vinkius's secure sandboxed environment and never exposed to the LLM. The server only transmits the resulting JSON payloads, such as dashboard configs and active alert states, directly to your LangChain agent over secure channels.

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