Documentation Grafana Cloud AI and machine learning Grafana Assistant Configure Grafana Cloud MCP

Grafana Cloud MCP server

The Grafana Cloud MCP server is a remotely hosted Model Context Protocol (MCP) server that lets external AI agents connect directly to your Grafana Cloud data. MCP-compatible clients, for example, Cursor, Claude Desktop, Windsurf, and Goose, can query metrics, logs, and other observability data from your Grafana environment without any local installation.

Unlike the open source Grafana MCP server, which runs locally and requires manual service account token configuration, the Grafana Cloud MCP server is fully hosted and uses OAuth 2.1 authorization. You point your AI agent at the Grafana Cloud MCP endpoint, authorize in your browser, and your agent connects.

How Grafana Cloud MCP differs from the local OSS server

The following table compares the Grafana Cloud MCP server with the local OSS MCP server.

Before you begin

Ensure you have the following:

• Grafana Cloud: The Grafana Cloud MCP server works only with hosted Grafana Cloud environments. Self-hosted Grafana users should use the local OSS MCP server
• Terms and conditions: An administrator must accept the Grafana Assistant terms and conditions
• Permissions: You need the Assistant Cloud MCP User role or the grafana-assistant-app.cloud-mcp:access permission. Users with the Editor role or higher have this permission by default. Refer to Manage Assistant access with RBAC for details
• MCP client: You need an MCP-compatible client, for example, Cursor, Claude Desktop, Windsurf, or Goose

Connect your AI agent

The following steps connect your AI agent to the Grafana Cloud MCP server.

1. Configure your MCP client using one of the methods below.
2. Run a prompt in your AI agent that requires Grafana data.
3. When prompted, authorize the connection in your browser.

Your AI agent is now connected to your Grafana data.

Quick install

Some clients support one-click or one-command installation:

• Cursor: Install Grafana MCP in Cursor
• Claude Code: Run claude mcp add grafana --transport http https://mcp.grafana.com/mcp in your terminal

Client configuration

Add the Grafana MCP server to your client’s configuration. Use the Streamable HTTP transport type (SSE isn’t supported).

Replace <your-stack> with your Grafana Cloud stack name. The X-Grafana-URL header is optional but recommended — it skips the URL entry step during authorization and redirects you directly to the consent page.

Cursor Claude-Desktop Claude-Code Windsurf VS-Code

Copy

Cursor Copy

{
  "mcpServers": {
    "grafana": {
      "url": "https://mcp.grafana.com/mcp",
      "headers": {
        "X-Grafana-URL": "https://<your-stack>.grafana.net"
      }
    }
  }
}

Claude-Desktop Copy

{
  "mcpServers": {
    "grafana": {
      "type": "http",
      "url": "https://mcp.grafana.com/mcp",
      "headers": {
        "X-Grafana-URL": "https://<your-stack>.grafana.net"
      }
    }
  }
}

Claude-Code Copy

claude mcp add grafana \
  --transport http \
  --header "X-Grafana-URL: https://<your-stack>.grafana.net" \
  https://mcp.grafana.com/mcp

Windsurf Copy

{
  "mcpServers": {
    "grafana": {
      "url": "https://mcp.grafana.com/mcp",
      "headers": {
        "X-Grafana-URL": "https://<your-stack>.grafana.net"
      }
    }
  }
}

VS-Code Copy

{
  "servers": {
    "grafana": {
      "type": "http",
      "url": "https://mcp.grafana.com/mcp",
      "headers": {
        "X-Grafana-URL": "https://<your-stack>.grafana.net"
      }
    }
  }
}

Where to add the configuration:

• Cursor: Settings > Features > MCP > + Add New MCP Server, or add to .cursor/mcp.json
• Claude Desktop: Add to claude_desktop_config.json
• Claude Code: Run the command in your terminal
• Windsurf: Add to ~/.codeium/windsurf/mcp_config.json
• VS Code: Add to .vscode/mcp.json in your workspace

For any other MCP-compatible client, set the endpoint to https://mcp.grafana.com/mcp with the Streamable HTTP transport type, and optionally set the X-Grafana-URL header to your Grafana Cloud instance URL.

Configure read and write access

When you authorize a Grafana Cloud MCP connection, the consent page shows the permissions the client is requesting. You can choose which permissions to grant:

• Read access: View dashboards, alerts, incidents, and query data sources. Always available
• Write access: Create and modify dashboards, alerts, and incidents. You can uncheck this to grant read-only access

If you don’t check Write access, the agent can only query and browse your Grafana data. Write tools, for example, update_dashboard and create_incident, aren’t available.

Organization Admins can grant write access by default. If the Write access checkbox is disabled on the consent page, ask your administrator to assign you the Assistant Admin role. Refer to Manage Assistant access with RBAC for details.

Explore available tools

The Grafana Cloud MCP server exposes the same tool categories as the open source Grafana MCP server, plus Assistant-native tools, for example, infrastructure memory. Tools marked Write require the grafana:write scope.

Search and navigation

Use these tools to find dashboards, folders, and generate links to Grafana resources.

Dashboards and folders

Use these tools to view and manage dashboards and folders.

Data sources

Use these tools to list and inspect configured data sources.

Prometheus

Use these tools to discover metrics and execute PromQL queries.

Loki

Use these tools to query logs and discover label metadata.

Tempo

If you have Tempo data sources in your Grafana Cloud stack, the Grafana Cloud MCP server will proxy any tools offered by that Tempo data source.

Pyroscope

Use these tools to query profiling data.

ClickHouse

Use these tools to query ClickHouse datasources.

CloudWatch

Use these tools to query AWS CloudWatch metrics.

Elasticsearch

Use this tool to search Elasticsearch datasources.

Alerting

Use these tools to view and manage alert rules and routing configuration.

Annotations

Use these tools to view and create annotations on dashboards.

Incidents

Use these tools to view and manage incidents.

OnCall

Use these tools to view on-call schedules, shifts, teams, and alert groups.

Sift

Use these tools to list and retrieve Sift investigations and analyses.

Other tools

Use these tools for additional Grafana tasks, including panel rendering and infrastructure summaries.

Manage connections

Manage your Grafana Cloud MCP connections from the Grafana Assistant Settings → External connections → MCP connections page in your Grafana Cloud stack.

Revoke access

To revoke a Grafana Cloud MCP connection before it expires, go to Settings → External connections → MCP connections and find the connection in the list.

Session lifetime

Your OAuth token is valid for 1 hour and refreshes automatically for 30 days. After 30 days, you’re prompted to log in and re-authorize.

Data privacy

Grafana securely routes your MCP queries via proxy. Grafana doesn’t train AI models on your PromQL, LogQL queries, or prompt payload data. Refer to Privacy and security for more information.

Billing and usage

The Grafana Cloud MCP server is part of Grafana Assistant. Users who connect through MCP are counted as active users and contribute to your organization’s monthly usage. The same fair usage limits and plan-level allowances apply whether you interact with Assistant through the Grafana UI or through an MCP client.

To monitor usage across all Assistant surfaces including MCP, navigate to Assistant > Usage in your Grafana Cloud stack. Refer to Pricing for full details on billing, limits, and access controls.

Known limitations

• Grafana Cloud only: The Grafana Cloud MCP server doesn’t support self-hosted Grafana instances. Self-hosted users should use the local OSS MCP server
• Transport: Only Streamable HTTP is supported. SSE transport isn’t supported

Next steps

• Pricing and usage
• Query data
• Run investigations
• Navigate Grafana resources