Skip to main content

Grafana MCP server

Grafana is the open-source analytics and visualization platform that connects with every database to create interactive dashboards and monitoring systems. With this MCP server, AI agents can create and manage dashboards, configure data sources, set up alerts, and manage users and permissions through natural language commands.

Setting up an MCP server

This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the individual application pages.

Before you begin​

You'll need:

  • Access to AI Gateway with permission to create MCP servers
  • API credentials for the application you're connecting (see the relevant application page for what to collect)

Create an MCP server​

Find the API in the catalog​

  1. Sign in to AI Gateway and select MCP Servers from the left navigation.
  2. Select New MCP Server.
  3. Search for the application you want to connect, then select it from the catalog.

Configure the server​

  1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
  2. Enter a Description so your team knows what the server is for.
  3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
  4. Toggle Production mode on if this server will be used in a live workflow.
  5. Select Next.

Configure authentication​

Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.

Configure security​

  1. Set any Rate limits appropriate for your use case and the API's own limits.
  2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
  3. Select Next.

Deploy​

Review the summary, then select Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.

Connect to an AI client​

Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:

Tips​

  • You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
  • If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
  • You can edit a server's name, description, timeout, and security settings after deployment without redeploying.

Authentication​

Grafana uses API keys or service accounts for programmatic access. Generate API keys from Grafana or create a service account with appropriate permissions.

  • API Key Header: Authorization: Bearer {api-key}
  • Base URL: https://your-grafana-instance.com/api
  • API Key Generation: Admin > API Keys (or Service Accounts on newer versions)
  • Permissions: Configure role-based access control for API keys

Available tools​

The Grafana MCP server exposes dashboard management, data source configuration, alerting, user management, and annotation APIs.

ToolPurpose
Dashboard ManagementCreate, update, delete dashboards; manage dashboard layouts; organize by folders
Panel ConfigurationAdd time series, gauge, stat, and table panels; configure queries; set visualization options
Data Source ManagementAdd and configure data sources; test connectivity; manage data source settings
Alert RulesCreate and manage alert rules; configure notification channels; set evaluation intervals
Annotation ManagementAdd deployment markers; create incident timeline annotations; correlate with metrics
User ManagementCreate users and teams; manage permissions; configure user preferences and roles
Folder OrganizationCreate folders; set folder permissions; organize dashboards hierarchically

Tips​

Use consistent color schemes and layouts and group related metrics logically.

Add helpful descriptions to explain metrics.

Test dashboards with different time ranges.

Set meaningful thresholds to avoid alert fatigue.

Use escalation policies for critical alerts.

Test notifications before production and include context in alert messages.

Use appropriate query intervals based on data granularity.

Enable caching where applicable.

Test data source performance with production data volumes.

Use teams to organize users by function.

Grant minimal necessary permissions and regularly review access controls.

Audit permission changes.

Regularly export dashboard JSON for version control.

Store configurations in Git.

Document dashboard purposes and dependencies and test restoration procedures.