G

Grafana MCP

Query dashboards, Prometheus, Loki, and incidents from Grafana.

Grafana Labs·No reviews yet
Repo Docs
Share:

About

Official Grafana MCP server: list and search dashboards, run Prometheus/PromQL and Loki/LogQL queries, inspect alerts and incidents in Grafana OnCall, and pull annotations. Works with self-hosted Grafana and Grafana Cloud.

Example tools

Illustrative tool names — the actual tool set is defined by the server at runtime.

list_resources
Enumerate resources exposed by this MCP
get_resource
Fetch a resource by ID
invoke
Invoke the primary action of this MCP

Screenshots

No screenshots yet.

Frequently Asked Questions

Common questions about Grafana MCP.

What is the Grafana MCP used for?
The Grafana MCP facilitates interaction with Grafana for tasks such as listing dashboards, executing Prometheus (PromQL) and Loki (LogQL) queries, and managing alerts in Grafana OnCall. It integrates with both self-hosted Grafana instances and Grafana Cloud.
How do I authenticate with the Grafana MCP?
Authentication for the Grafana MCP requires an API key. This API key needs to be configured in your MCP client to establish a secure connection with your Grafana instance, allowing access to its features.
Can I query Prometheus and Loki using this MCP?
Yes, you can run Prometheus (PromQL) and Loki (LogQL) queries directly through the Grafana MCP. This enables programmatic access to your metrics and logs stored in Grafana, streamlining observability workflows.
What are typical deployment scenarios for the Grafana MCP?
The Grafana MCP can connect to both self-hosted Grafana deployments and Grafana Cloud instances. This flexibility supports a range of environments, from private data centers to cloud-native monitoring setups, adapting to your existing Grafana infrastructure.
Does using the Grafana MCP incur additional costs?
The Grafana MCP itself is OSS but its usage costs depend on your underlying Grafana deployment. If you are using Grafana Cloud, typical usage and data ingress/egress costs apply. For self-hosted Grafana, specific costs relate to your infrastructure and operational overhead.
What is a common limitation when using the Grafana MCP?
A common limitation is that the effectiveness of the Grafana MCP is directly tied to the permissions granted to the API key used for authentication. If the API key has restricted access, certain Grafana features or data might not be accessible through the MCP, requiring careful permission management.

Install Grafana MCP

Claude Desktop

Add this to claude_desktop_config.json.

{
  "mcpServers": {
    "grafana": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-grafana"
      ]
    }
  }
}

Cursor

Add this to ~/.cursor/mcp.json.

{
  "mcpServers": {
    "grafana": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-grafana"
      ]
    }
  }
}

VS Code

Add this to your workspace settings.json.

{
  "mcp.servers": {
    "grafana": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-grafana"
      ]
    }
  }
}

Reviews

Sign in to leave a review.

No reviews yet. Be the first!

Discussion(0)

Sign in to join the discussion.

No comments yet.