GRAFANA TOOLS

29 tools from the Grafana MCP Server, categorised by risk level.

READ 25 tools
Read generate_deeplinks Create accurate Grafana resource URLs Read get_dashboard_by_uid Retrieve complete dashboard details by UID Read get_dashboard_panel_queries Extract panel titles, queries, and datasource info Read get_dashboard_property Extract specific dashboard parts using JSONPath Read get_dashboard_summary Get compact dashboard overview without full JSON Read get_datasource Retrieve datasource details by UID or name Read get_panel_image Render a dashboard panel as PNG Read get_query_examples Get sample queries for learning syntax Read get_role_details Inspect role permissions in Grafana Read list_alert_rules View alerting configurations Read list_all_roles List all available roles Read list_annotations Query dashboard annotations Read list_cloudwatch_namespaces List AWS CloudWatch service namespaces Read list_datasources View all configured datasources Read list_incidents Browse Grafana Incident records Read list_loki_label_names Explore log label names in Loki Read list_prometheus_metric_names Discover available Prometheus metrics Read list_teams View Grafana teams Read list_users_by_org List users in an organisation Read query_clickhouse Execute SQL queries on ClickHouse Read query_cloudwatch Run AWS CloudWatch metric queries Read query_elasticsearch Search using Lucene or Query DSL Read query_loki_logs Run LogQL queries for logs and metrics Read query_prometheus Execute PromQL queries against Prometheus Read search_dashboards Search dashboards by title or metadata
How many tools does the Grafana MCP server have? +

The Grafana MCP server exposes 29 tools across 2 categories: Read, Write.

How do I enforce policies on Grafana tools? +

Route the Grafana server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Grafana tools fall into? +

Grafana tools are categorised as Read (25), Write (4). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.