Integration

Grafana integration

Grafana observability platform API for managing dashboards, data sources, alerts, and annotations. Create and update dashboards, configure alerts, manage organizations, and query data sources for monitoring and visualization.

Connect Grafana How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Grafana.Built from the 29 Grafana tools below, on the connection you add once.

Common Grafana use cases

automate datasource management
automate folder management
automate snapshot management
automate dashboard management
automate annotation management
automate alert rule management
list team programmatically
list user programmatically
get folder programmatically
list folder programmatically

What you can do with Grafana

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Datasource, 6 operations

create_datasourceCreate datasourcePOSTCreate a new data source in the current organization. Supports all Grafana data source types including Prometheus, Loki, Elasticsearch, InfluxDB, and more. Returns the created data source with its assigned ID.
delete_datasourceDelete datasourceDELETEDelete a data source by its unique identifier (UID). This permanently removes the data source configuration. Dashboards referencing this data source will lose their data connection.
get_datasource_by_idGet datasource by idGETGet a specific data source by its unique identifier (UID). Returns full data source configuration including name, type, URL, access mode, and JSON data settings.
list_datasourcesList datasourcesGETList all configured data sources in the current organization. Returns data source names, types, URLs, access modes, and configuration details. Useful for discovering available data sources.
query_datasourceQuery datasourcePOSTExecute queries against one or more data sources using the unified query API. Supports all data source types. Returns query results with frames of data suitable for visualization or processing.
update_datasourceUpdate datasourcePUTUpdate an existing data source by its unique identifier (UID). Replaces the data source configuration with the provided values. Returns the updated data source details.

Folder, 4 operations

create_folderCreate folderPOSTCreate a new folder for organizing dashboards. Folders can have permissions that are inherited by their dashboards. Returns the created folder with its generated UID and ID.
delete_folderDelete folderDELETEDelete a folder by its unique identifier (UID). This also deletes all dashboards contained within the folder. Returns a confirmation message upon success.
get_folderGet folderGETGet a folder by its unique identifier (UID). Returns the folder title, ID, UID, and metadata including creation and update timestamps.
list_foldersList foldersGETList all folders in the current organization. Returns folder UIDs, titles, and IDs. Folders are used to organize dashboards and manage permissions.

Annotation, 3 operations

create_annotationCreate annotationPOSTCreate a new annotation to mark a point or region in time on a dashboard. Annotations can be global or associated with a specific dashboard and panel. Useful for marking deployments, incidents, or other events.
delete_annotationDelete annotationDELETEDelete an annotation by its numeric ID. This permanently removes the annotation from all dashboards where it appears.
list_annotationsList annotationsGETList annotations matching the specified filters. Annotations are used to mark points in time on graphs with events, deployments, or other significant occurrences. Supports filtering by dashboard, panel, tags, and time range.

Dashboard, 3 operations

delete_dashboard_by_uidDelete dashboard by uidDELETEDelete a dashboard by its unique identifier (UID). This permanently removes the dashboard and all its panels. Returns a confirmation message upon success.
get_dashboard_by_uidGet dashboard by uidGETGet a dashboard by its unique identifier (UID). Returns the full dashboard model including panels, templating, time settings, and metadata such as version, folder, and creation date.
search_dashboardsSearch dashboardsGETSearch for dashboards and folders by title, tag, or type. Returns a list of matching dashboards with their UIDs, titles, URLs, tags, and folder information. Supports pagination for large result sets.

Snapshot, 3 operations

create_snapshotCreate snapshotPOSTCreate a dashboard snapshot that can be shared externally without requiring authentication. Snapshots capture the current state of a dashboard including all panel data. Returns the snapshot URL and delete key.
delete_snapshotDelete snapshotDELETEDelete a dashboard snapshot by its key. This permanently removes the snapshot and its shared URL will no longer be accessible.
list_snapshotsList snapshotsGETList all dashboard snapshots. Optionally filter by name query and limit the number of results returned. Returns snapshot keys, names, and URLs.

Alert rule, 2 operations

delete_alert_ruleDelete alert ruleDELETEDelete a specific Grafana-managed alert rule by its namespace, group, and unique identifier (UID). This permanently removes the alert rule and stops its evaluation.
list_alert_rulesList alert rulesGETList all Grafana-managed alert rules across all namespaces (folders). Returns alert rules grouped by namespace and rule group, including conditions, queries, labels, and evaluation intervals.

Current org, 1 operation

get_current_orgGet current orgGETGet the current organization details for the authenticated user. Returns organization ID, name, and address information. Useful for verifying which organization context the API key belongs to.

Current user, 1 operation

get_current_userGet current userGETGet the profile of the currently authenticated user. Returns user ID, email, name, login, theme preference, and organization details.

Home dashboard, 1 operation

get_home_dashboardGet home dashboardGETGet the home dashboard for the current user. Returns the dashboard configured as the home/default dashboard, or the default Grafana home dashboard if none is configured.

Org user, 1 operation

get_org_usersGet org usersGETGet all users within the current organization. Returns user IDs, logins, emails, names, and their roles (Admin, Editor, Viewer) within the organization.

Team, 1 operation

list_teamsList teamsGETSearch for teams in the current organization. Teams are used to manage dashboard permissions and organize users. Returns team names, IDs, member counts, and email addresses.

Update alert rule, 1 operation

create_update_alert_ruleCreate update alert rulePOSTCreate or update alert rules within a specific namespace (folder). Provide a rule group containing one or more alert rules with their queries, conditions, and notification settings.

Update dashboard, 1 operation

create_update_dashboardCreate update dashboardPOSTCreate a new dashboard or update an existing one. Provide the full dashboard model in the request body. Set 'overwrite' to true to update existing dashboards. Returns the dashboard UID, ID, URL, and version.

User, 1 operation

list_usersList usersGETList all Grafana users (server admin only). Returns user IDs, logins, emails, names, and admin status. For organization-scoped user lists, use the get_org_users endpoint instead.

Use Grafana from Claude Code, Cursor or Codex

Connect Grafana in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Grafana operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Grafana

Create your workspace
Sign up free. Nothing to install.
Connect Grafana once
Add your Grafana connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Grafana integration FAQ

What can you do with the Grafana integration?

LiveContext exposes 29 operations on Grafana, covering datasource, folder, annotation and dashboard. Common uses include automate datasource management, automate folder management and automate snapshot management.