// SCAN REPORT

Mcp Read Only Grafana

57 tools. 18 can modify or destroy data without limits.

5 destructive tools with no built-in limits. Policy required.

Last updated: 29 Jun 2026

18 can modify or destroy data

39 read-only

57 tools total

Community server · catalogue entry verified 29/06/2026

How to control Mcp Read Only Grafana ↓

TOOL MAP

What Mcp Read Only Grafana exposes to your agents

Read (39) Write / Execute (13) Destructive / Financial (5)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mcp Read Only Grafana tools

Destructive · High delete_alert_rule Deleting alert rules is an irreversible action that removes monitoring configurations and cannot be undone without manual recreation. Destructive · High delete_contact_point Deletion of contact points is irreversible—once removed, notification routing is lost and cannot be automatically restored without reconfiguration. Destructive · High delete_mute_timing The 'delete' prefix establishes this as a Destructive action—it removes data that cannot be recovered without manual restoration or backups. Destructive · High delete_notification_policies Deleting notification policies is an irreversible, destructive action that cannot be undone and removes critical configurations governing alert notifications.

18 of Mcp Read Only Grafana's 57 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp Read Only Grafana

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Read Only Grafana, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_alert_rule": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_alert_rule": {
    "limits": [
      {
        "counter": "create_alert_rule_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "explore_query": {
    "limits": [
      {
        "counter": "explore_query_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mcp Read Only Grafana — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP READ ONLY GRAFANA →

Instant setup, no code required.

FULL CATALOGUE

All 57 Mcp Read Only Grafana tools

DESTRUCTIVE 5 tools

Destructive delete_alert_rule delete_alert_rule Destructive delete_contact_point delete_contact_point Destructive delete_mute_timing delete_mute_timing Destructive delete_notification_policies delete_notification_policies Destructive delete_notification_template delete_notification_template

WRITE 13 tools

Write create_alert_rule create_alert_rule Write create_contact_point create_contact_point Write create_folder create_folder Write create_mute_timing create_mute_timing Write export_alert_rule [WRITE] Export a specific alert rule in provisioning format. Write export_all_alert_rules [WRITE] Export all alert rules in provisioning format. Write save_dashboard save_dashboard Write set_notification_policies set_notification_policies Write set_notification_template set_notification_template Write update_alert_rule update_alert_rule Write update_contact_point update_contact_point Write update_mute_timing update_mute_timing Write update_rule_group update_rule_group

READ 39 tools

Read explore_query explore_query Read export_rule_group export_rule_group Read get_alert_rule_by_uid Get detailed information about a specific alert rule. Read get_alert_rules_with_state get_alert_rules_with_state Read get_alert_state_history get_alert_state_history Read get_current_org Get current organization information. Read get_current_user get_current_user Read get_dashboard get_dashboard Read get_dashboard_info get_dashboard_info Read get_dashboard_panel get_dashboard_panel Read get_dashboard_panels get_dashboard_panels Read get_dashboard_versions Get version history of a dashboard. Read get_datasource_health get_datasource_health Read get_firing_alerts get_firing_alerts Read get_health Check Grafana instance health and version information. Read get_mute_timing [WRITE] Get a specific mute timing by name. Read get_notification_policies [WRITE] Get the notification policy tree. Read get_notification_template [WRITE] Get a specific notification template by name. Read get_provisioned_alert_rule [WRITE] Get a specific alert rule by UID from the provisioning API. Read get_rule_group [WRITE] Get a specific alert rule group. Read get_ruler_group get_ruler_group Read get_ruler_namespace_rules Get all rule groups for a specific namespace (folder). Read get_ruler_rules get_ruler_rules Read get_user_permissions get_user_permissions Read list_alerts List alert rules, optionally filtered by folder. Read list_annotations list_annotations Read list_connections List all available Grafana connections with their configuration details. Read list_contact_points [WRITE] Get all contact points. Read list_datasources List all configured data sources in Grafana. Read list_folder_dashboards list_folder_dashboards Read list_folders List all folders in the Grafana instance. Read list_mute_timings [WRITE] Get all mute timings. Read list_notification_templates [WRITE] Get all notification templates. Read list_provisioned_alert_rules [WRITE] Fetch all provisioned alert rules via the read-only provisioning API. Read list_teams list_teams Read list_users list_users Read query_loki query_loki Read query_prometheus query_prometheus Read search_dashboards search_dashboards

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mcp Read Only Grafana

Can an AI agent delete data through the Mcp Read Only Grafana MCP server? +

Yes. The Mcp Read Only Grafana server exposes 5 destructive tools including delete_alert_rule, delete_contact_point, delete_mute_timing. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mcp Read Only Grafana? +

The Mcp Read Only Grafana server has 13 write tools including create_alert_rule, create_contact_point, create_folder. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Mcp Read Only Grafana.

How many tools does the Mcp Read Only Grafana MCP server expose? +

57 tools across 3 categories: Destructive, Read, Write. 39 are read-only. 18 can modify, create, or delete data.

How do I enforce a policy on Mcp Read Only Grafana? +

Register the Mcp Read Only Grafana MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mcp Read Only Grafana tool call.

Deterministic rules across all 57 Mcp Read Only Grafana tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP READ ONLY GRAFANA →

Instant setup, no code required.

57 Mcp Read Only Grafana tools catalogued and risk-classified — across an index of 43,000+ MCP servers.