Grafana

Grafana MCP Server

MCP server for Grafana.

What is an MCP Server?⁠

MCP Info

Image Building Info

Attribute	Details
Dockerfile	https://github.com/grafana/mcp-grafana/blob/6b999bc8bd4247257e3afc286ae9a2418e5fe13d/Dockerfile⁠
Docker Image built by	Docker Inc.
Docker Scout Health Score
Verify Signature	COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/grafana --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub
Licence	Apache License 2.0

Available Tools (50)

Tools Details

Tool: add_activity_to_incident

Add a note (userNote activity) to an existing incident's timeline using its ID. The note body can include URLs which will be attached as context. Use this to add context to an incident.

Tool: create_alert_rule

Creates a new Grafana alert rule with the specified configuration. Requires title, rule group, folder UID, condition, query data, no data state, execution error state, and duration settings.

Tool: create_folder

Create a Grafana folder. Provide a title and optional UID. Returns the created folder.

Tool: create_incident

Create a new Grafana incident. Requires title, severity, and room prefix. Allows setting status and labels. This tool should be used judiciously and sparingly, and only after confirmation from the user, as it may notify or alarm lots of people.

Tool: delete_alert_rule

Deletes a Grafana alert rule by its UID. This action cannot be undone.

Tool: fetch_pyroscope_profile

Fetches a profile from a Pyroscope data source for a given time range. By default, the time range is tha past 1 hour. The profile type is required, available profile types can be fetched via the list_pyroscope_profile_types tool. Not all profile types are available for every service. Expect some queries to return empty result sets, this indicates the profile type does not exist for that query. In such a case, consider trying a related profile type or giving up. Matchers are not required, but highly recommended, they are generally used to select an application by the service_name label (e.g. {service_name="foo"}). Use the list_pyroscope_label_names tool to fetch available label names, and the list_pyroscope_label_values tool to fetch available label values. The returned profile is in DOT format.

This tool is read-only. It does not modify its environment.

Tool: find_error_pattern_logs

Searches Loki logs for elevated error patterns compared to the last day's average, waits for the analysis to complete, and returns the results including any patterns found.

This tool is read-only. It does not modify its environment.

Tool: find_slow_requests

Searches relevant Tempo datasources for slow requests, waits for the analysis to complete, and returns the results.

This tool is read-only. It does not modify its environment.

Tool: generate_deeplink

Generate deeplink URLs for Grafana resources. Supports dashboards (requires dashboardUid), panels (requires dashboardUid and panelId), and Explore queries (requires datasourceUid). Optionally accepts time range and additional query parameters.

This tool is read-only. It does not modify its environment.

Tool: get_alert_group

Get a specific alert group from Grafana OnCall by its ID. Returns the full alert group details.

This tool is read-only. It does not modify its environment.

Tool: get_alert_rule_by_uid

Retrieves the full configuration and detailed status of a specific Grafana alert rule identified by its unique ID (UID). The response includes fields like title, condition, query data, folder UID, rule group, state settings (no data, error), evaluation interval, annotations, and labels.

This tool is read-only. It does not modify its environment.

Tool: get_assertions

Get assertion summary for a given entity with its type, name, env, site, namespace, and a time range

This tool is read-only. It does not modify its environment.

Tool: get_current_oncall_users

Get the list of users currently on-call for a specific Grafana OnCall schedule ID. Returns the schedule ID, name, and a list of detailed user objects for those currently on call.

This tool is read-only. It does not modify its environment.

Tool: get_dashboard_by_uid

Retrieves the complete dashboard, including panels, variables, and settings, for a specific dashboard identified by its UID. WARNING: Large dashboards can consume significant context window space. Consider using get_dashboard_summary for overview or get_dashboard_property for specific data instead.

This tool is read-only. It does not modify its environment.

Tool: get_dashboard_panel_queries

Use this tool to retrieve panel queries and information from a Grafana dashboard. When asked about panel queries, queries in a dashboard, or what queries a dashboard contains, call this tool with the dashboard UID. The datasource is an object with fields uid (which may be a concrete UID or a template variable like "$datasource") and type. If the datasource UID is a template variable, it won't be usable directly for queries. Returns an array of objects, each representing a panel, with fields: title, query, and datasource (an object with uid and type).

This tool is read-only. It does not modify its environment.

Tool: get_dashboard_property

Get specific parts of a dashboard using JSONPath expressions to minimize context window usage. Common paths: '$.title' (title), '$.panels[].title' (all panel titles), '$.panels[0]' (first panel), '$.templating.list' (variables), '$.tags' (tags), '$.panels[].targets[*].expr' (all queries). Use this instead of get_dashboard_by_uid when you only need specific dashboard properties.

This tool is read-only. It does not modify its environment.

Tool: get_dashboard_summary

Get a compact summary of a dashboard including title, panel count, panel types, variables, and other metadata without the full JSON. Use this for dashboard overview and planning modifications without consuming large context windows.

This tool is read-only. It does not modify its environment.

Tool: get_datasource_by_name

Retrieves detailed information about a specific datasource using its name. Returns the full datasource model, including UID, type, URL, access settings, JSON data, and secure JSON field status.

This tool is read-only. It does not modify its environment.

Tool: get_datasource_by_uid

Retrieves detailed information about a specific datasource using its UID. Returns the full datasource model, including name, type, URL, access settings, JSON data, and secure JSON field status.

This tool is read-only. It does not modify its environment.

Tool: get_incident

Get a single incident by ID. Returns the full incident details including title, status, severity, labels, timestamps, and other metadata.

This tool is read-only. It does not modify its environment.

Tool: get_oncall_shift

Get detailed information for a specific Grafana OnCall shift using its ID. A shift represents a designated time period within a schedule when users are actively on-call. Returns the full shift details.

This tool is read-only. It does not modify its environment.

Tool: get_sift_analysis

Retrieves a specific analysis from an investigation by its UUID. The investigation ID and analysis ID should be provided as strings in UUID format.

This tool is read-only. It does not modify its environment.

Tool: get_sift_investigation

Retrieves an existing Sift investigation by its UUID. The ID should be provided as a string in UUID format (e.g. '02adab7c-bf5b-45f2-9459-d71a2c29e11b').

This tool is read-only. It does not modify its environment.

Tool: list_alert_groups

List alert groups from Grafana OnCall with filtering options. Supports filtering by alert group ID, route ID, integration ID, state (new, acknowledged, resolved, silenced), team ID, time range, labels, and name. For time ranges, use format '{start}_{end}' ISO 8601 timestamp range (e.g., '2025-01-19T00:00:00_2025-01-19T23:59:59' for a specific day). For labels, use format 'key:value' (e.g., ['env:prod', 'severity:high']). Returns a list of alert group objects with their details. Supports pagination.

This tool is read-only. It does not modify its environment.

Tool: list_alert_rules

Lists Grafana alert rules, returning a summary including UID, title, current state (e.g., 'pending', 'firing', 'inactive'), and labels. Supports filtering by labels using selectors and pagination. Example label selector: [{'name': 'severity', 'type': '=', 'value': 'critical'}]. Inactive state means the alert state is normal, not firing

This tool is read-only. It does not modify its environment.

Tool: list_contact_points

Lists Grafana notification contact points, returning a summary including UID, name, and type for each. Supports filtering by name - exact match - and limiting the number of results.

This tool is read-only. It does not modify its environment.

Tool: list_datasources

List available Grafana datasources. Optionally filter by datasource type (e.g., 'prometheus', 'loki'). Returns a summary list including ID, UID, name, type, and default status.

This tool is read-only. It does not modify its environment.

Tool: list_incidents

List Grafana incidents. Allows filtering by status ('active', 'resolved') and optionally including drill incidents. Returns a preview list with basic details.

This tool is read-only. It does not modify its environment.

Tool: list_loki_label_names

Lists all available label names (keys) found in logs within a specified Loki datasource and time range. Returns a list of unique label strings (e.g., ["app", "env", "pod"]). If the time range is not provided, it defaults to the last hour.

This tool is read-only. It does not modify its environment.

Tool: list_loki_label_values

Retrieves all unique values associated with a specific labelName within a Loki datasource and time range. Returns a list of string values (e.g., for labelName="env", might return ["prod", "staging", "dev"]). Useful for discovering filter options. Defaults to the last hour if the time range is omitted.

This tool is read-only. It does not modify its environment.

Tool: list_oncall_schedules

List Grafana OnCall schedules, optionally filtering by team ID. If a specific schedule ID is provided, retrieves details for only that schedule. Returns a list of schedule summaries including ID, name, team ID, timezone, and shift IDs. Supports pagination.

This tool is read-only. It does not modify its environment.

Tool: list_oncall_teams

List teams configured in Grafana OnCall. Returns a list of team objects with their details. Supports pagination.

This tool is read-only. It does not modify its environment.

Tool: list_oncall_users

List users from Grafana OnCall. Can retrieve all users, a specific user by ID, or filter by username. Returns a list of user objects with their details. Supports pagination.

This tool is read-only. It does not modify its environment.

Tool: list_prometheus_label_names

List label names in a Prometheus datasource. Allows filtering by series selectors and time range.

This tool is read-only. It does not modify its environment.

Tool: list_prometheus_label_values

Get the values for a specific label name in Prometheus. Allows filtering by series selectors and time range.

This tool is read-only. It does not modify its environment.

Tool: list_prometheus_metric_metadata

List Prometheus metric metadata. Returns metadata about metrics currently scraped from targets. Note: This endpoint is experimental.

This tool is read-only. It does not modify its environment.

Tool: list_prometheus_metric_names

List metric names in a Prometheus datasource. Retrieves all metric names and then filters them locally using the provided regex. Supports pagination.

This tool is read-only. It does not modify its environment.

Tool: list_pyroscope_label_names

Lists all available label names (keys) found in profiles within a specified Pyroscope datasource, time range, and optional label matchers. Label matchers are typically used to qualify a service name ({service_name="foo"}). Returns a list of unique label strings (e.g., ["app", "env", "pod"]). Label names with double underscores (e.g. name) are internal and rarely useful to users. If the time range is not provided, it defaults to the last hour.

This tool is read-only. It does not modify its environment.

Tool: list_pyroscope_label_values

Lists all available label values for a particular label name found in profiles within a specified Pyroscope datasource, time range, and optional label matchers. Label matchers are typically used to qualify a service name ({service_name="foo"}). Returns a list of unique label strings (e.g. for label name "env": ["dev", "staging", "prod"]). If the time range is not provided, it defaults to the last hour.

This tool is read-only. It does not modify its environment.

Tool: list_pyroscope_profile_types

Lists all available profile types available in a specified Pyroscope datasource and time range. Returns a list of all available profile types (example profile type: "process_cpu:cpu:nanoseconds:cpu:nanoseconds"). A profile type has the following structure: ::::. Not all profile types are available for every service. If the time range is not provided, it defaults to the last hour.

This tool is read-only. It does not modify its environment.

Tool: list_sift_investigations

Retrieves a list of Sift investigations with an optional limit. If no limit is specified, defaults to 10 investigations.

This tool is read-only. It does not modify its environment.

Tool: list_teams

Search for Grafana teams by a query string. Returns a list of matching teams with details like name, ID, and URL.

This tool is read-only. It does not modify its environment.

Tool: list_users_by_org

List users by organization. Returns a list of users with details like userid, email, role etc.

Tool: query_loki_logs

Executes a LogQL query against a Loki datasource to retrieve log entries or metric values. Returns a list of results, each containing a timestamp, labels, and either a log line (line) or a numeric metric value (value). Defaults to the last hour, a limit of 10 entries, and 'backward' direction (newest first). Supports full LogQL syntax for log and metric queries (e.g., {app="foo"} |= "error", rate({app="bar"}[1m])). Prefer using query_loki_stats first to check stream size and list_loki_label_names and list_loki_label_values to verify labels exist.

This tool is read-only. It does not modify its environment.

Tool: query_loki_stats

Retrieves statistics about log streams matching a given LogQL selector within a Loki datasource and time range. Returns an object containing the count of streams, chunks, entries, and total bytes (e.g., {"streams": 5, "chunks": 50, "entries": 10000, "bytes": 512000}). The logql parameter must be a simple label selector (e.g., {app="nginx", env="prod"}) and does not support line filters, parsers, or aggregations. Defaults to the last hour if the time range is omitted.

This tool is read-only. It does not modify its environment.

Tool: query_prometheus

Query Prometheus using a PromQL expression. Supports both instant queries (at a single point in time) and range queries (over a time range). Time can be specified either in RFC3339 format or as relative time expressions like 'now', 'now-1h', 'now-30m', etc.

This tool is read-only. It does not modify its environment.

Tool: search_dashboards

Search for Grafana dashboards by a query string. Returns a list of matching dashboards with details like title, UID, folder, tags, and URL.

This tool is read-only. It does not modify its environment.

Tool: search_folders

Search for Grafana folders by a query string. Returns matching folders with details like title, UID, and URL.

This tool is read-only. It does not modify its environment.

Tool: update_alert_rule

Updates an existing Grafana alert rule identified by its UID. Requires all the same parameters as creating a new rule.

Tool: update_dashboard

Create or update a dashboard using either full JSON or efficient patch operations. For new dashboards, provide the 'dashboard' field. For updating existing dashboards, use 'uid' + 'operations' for better context window efficiency. Patch operations support complex JSONPaths like '$.panels[0].targets[0].expr', '$.panels[1].title', '$.panels[2].targets[0].datasource', etc. Supports appending to arrays using '/- ' syntax: '$.panels/- ' appends to panels array, '$.panels[2]/- ' appends to nested array at index 2.

This tool may perform destructive updates.

Use this MCP Server

{
  "mcpServers": {
    "grafana": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GRAFANA_URL",
        "-e",
        "GRAFANA_API_KEY",
        "mcp/grafana",
        "--transport=stdio"
      ],
      "env": {
        "GRAFANA_URL": "http://localhost:3000",
        "GRAFANA_API_KEY": "<your service account token>"
      }
    }
  }
}

Why is it safer to run MCP Servers with Docker?⁠