Connect your account, then chat with AI to run tools.
Search Grafana dashboards, inspect data sources, review alerts, manage annotations, and summarize observability context from chat.
Try this workflow
Find service dashboards
Search Grafana dashboards for this service, list matching dashboards and folders, then summarize which dashboard looks most useful for triage.
Opens MCPBundles Studio with this server selected. After sign-in, chat and run tools from the same thread.
Browse all toolsBuilt for
SRE, DevOps, platform engineering, incident response, observability teams
Find service dashboards
Uses dashboard search to orient incident response.
Search Grafana dashboards for this service, list matching dashboards and folders, then summarize which dashboard looks most useful for triage.
Review alert status
Connects alert data to operational triage.
List Grafana alert rules, identify firing or recently changed alerts, and summarize which services need attention.
Map observability sources
Helps agents understand the observability backend landscape.
List Grafana data sources and explain what metrics, logs, or traces backends are connected for this organization.
Mark an incident
Uses annotations to connect operational events to dashboards.
Create a Grafana annotation for this deployment window with incident tags and a short description for later dashboard review.
What Grafana workflows can MCPBundles support?
It can inspect instance health, organizations, dashboards, folders, data sources, alert rules, and annotations available to the connected service account.
Does this work with Grafana Cloud and self-hosted Grafana?
Yes. Grafana Cloud uses a public stack URL. Self-hosted localhost instances can be reached through the MCPBundles desktop proxy.
What identifiers matter in Grafana?
Dashboards are best addressed by UID rather than numeric ID because UIDs are stable across many dashboard operations.
Related editorial
Grafana Workflows with AI
How AI agents can search dashboards, query datasources, debug alerts, and annotate incidents during an investigation.
Domain knowledge for Grafana — workflow patterns, data models, and gotchas for your AI agent.
Open-source observability platform for metrics, logs, and traces. Connects to data sources like Prometheus, Loki, InfluxDB, Elasticsearch, CloudWatch, and many more.
Create an annotation in Grafana to mark events like deployments, incidents, or configuration changes. Annotations appear as vertical markers on dashbo...
Create a new incident in Grafana Incident.
Delete a Grafana alert rule by UID.
Get the current state of all alert instances. Shows which alerts are firing, pending, or normal.
Get detailed information about a single Grafana alert rule by UID.
Get a Grafana dashboard by UID. Returns the full dashboard model including panels, queries, variables, annotations, and layout.
Get the title, query expressions, and datasource info for every panel in a dashboard. Useful for understanding what a dashboard monitors without loadi...
Get a compact overview of a dashboard — title, panel count, panel types, variables, and metadata — without the full JSON. Minimizes context usage.
Get detailed information about a Grafana data source by UID. Includes type, connection URL, database, access mode, and JSON configuration.
Check the health and version of the connected Grafana instance.
Get detailed information about a specific Grafana incident by ID.
Get all values for a specific Loki label name.
Get the notification policy routing tree that controls how alerts are routed to contact points.
Get detailed information about a specific on-call shift.
Get details about the current Grafana organization — name, ID, and address.
Get all values for a specific Prometheus label name.
Get metric metadata (type, help text, unit) from a Prometheus datasource. Useful for understanding what a metric measures before querying it.
List all alert rules in Grafana unified alerting. Shows rule name, condition, folder, status, and evaluation interval.
List annotations from Grafana. Annotations are event markers on dashboards used to mark deployments, incidents, or notable events. Filter by dashboard...
List available annotation tags with their usage counts.
List all notification contact points configured in Grafana alerting.
List all data sources in the Grafana instance. Shows type (Prometheus, Loki, Postgres, etc.), name, URL, and access mode.
List all folders in Grafana. Folders organize dashboards into logical groups.
List incidents from Grafana Incident. Filter by status (active/resolved).
List available label names from a Loki datasource.
List alert groups from Grafana OnCall. Filter by status.
List all on-call schedules from Grafana OnCall.
List all teams in Grafana OnCall.
List all users registered in Grafana OnCall.
List available label names from a Prometheus datasource.
List available metric names from a Prometheus datasource. Optionally filter by a series selector.
List all teams configured in the Grafana organization.
List all users in the current Grafana organization.
Execute LogQL queries against a Loki datasource through Grafana. Supports log queries (returns log lines) and metric queries (returns time series). Us...
Execute PromQL queries against a Prometheus datasource through Grafana. Supports instant queries (current value) and range queries (time series). Use ...
Search dashboards and folders in Grafana. Filter by query string, tag, type, or starred status. Returns dashboard UIDs, titles, URLs, and tags.
Update specific fields of an existing Grafana annotation (partial update).
Create a new alert rule or update an existing one. Include 'uid' in the rule object for updates.
Create a new dashboard or update an existing one. Include 'uid' and 'version' in the dashboard JSON for updates. Omit 'uid' or set 'id' to null for ne...
Grafana MCP server for observability and monitoring. Search dashboards, explore datasources, query alerts, manage annotations, and monitor your infrastructure — works with Grafana Cloud or self-hosted instances via the desktop proxy. It provides 39 tools that AI agents can use through the Model Context Protocol (MCP).
Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/grafana. Authentication is handled automatically.
Grafana provides 39 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.
Grafana uses API Key. Grafana requires credentials. Connect via MCPBundles and authentication is handled automatically.
It can inspect instance health, organizations, dashboards, folders, data sources, alert rules, and annotations available to the connected service account.
Yes. Grafana Cloud uses a public stack URL. Self-hosted localhost instances can be reached through the MCPBundles desktop proxy.
Dashboards are best addressed by UID rather than numeric ID because UIDs are stable across many dashboard operations.
The strongest workflows are incident triage, dashboard discovery, alert summaries, data-source mapping, and deployment annotations.
Connect Grafana to any MCP client in minutes
The link prefills the Add custom connector dialog — you still review the values and click Add, then Connect to complete OAuth.
Grafana and paste the MCP URL into Remote MCP server URL.Custom connectors at claude.ai require a paid Claude plan (Pro, Max, Team, or Enterprise).
More analytics integrations you might like
1Forge provides real-time and historical financial market data including forex exchange rates, crypt...
This server provides analytics tools for understanding user behavior and campaign performance. It is...
Anzenna offers a specialized platform for real-time data processing and analysis, enabling users to ...
Apify is a web scraping and automation platform for extracting data from websites at scale. Search t...
Appfigures is an analytics platform that provides app developers with insights into app performance,...
Appfollow provides tools for app management and optimization, offering insights on app performance, ...