Grafana MCP Server by DrDroid

Use the Grafana MCP Server to let AI enrich alerts, Automate diagnostics and resolve incidents faster - on top of your existing Grafana setup.

Start Free Trial

Turn Grafana Alerts into Actionable Insights

Grafana gives you visibility. DrDroid's Grafana MCP Server gives you answers.


Instead of shifting through dashboards and logs during every incident, the DrDroid's Grafana MCP server adds a layer of intelligence - enriching alerts with context, correlating signals, and suggesting next steps automatically

Less guesswork. Faster resolution. Fewer 3 AM escalations.
Grafana
Intelligence
Automation

What You Can Do

Powerful Capabilities to enhance your Grafana experience

Visualization Dashboard

Create comprehensive monitoring views with real-time metrics and interactive charts for your system performance.

Query Dashboard Panel Metrics

Execute specific Grafana dashboard panel queries to extract targeted metrics for your analysis needs.

Execute All Dashboard Panels

Run queries across all panels within a Grafana dashboard simultaneously for complete system visibility.

Metric Analysis

Pull service-level metrics and detect anomalies with powerful visualization tools that highlight critical trends.

Auto-Generated Dashboards

Fetch key widgets and automatically highlight important changes in your monitoring environment.

Seamless Integration

Connect your existing Grafana dashboards with our platform for enhanced monitoring capabilities and insights.

Seamless Integration

Connect your existing Grafana dashboards with our platform for enhanced monitoring capabilities and insights.

Seamless Integration

Connect your existing Grafana dashboards with our platform for enhanced monitoring capabilities and insights.

How It Works

1

Sign up to DrDroid

1-Click signup

Connect your alerts & Grafana

1-Click signup

2

Let AI do the work using MCP Servers

1-Click signup

3

You Act

1-Click signup

4

Ready for AI-Powered ops?

Start usign DrDroid to automate operations, reduce escalations and cut MTTR.

Start Free Trial
SOC 2 Type II
certifed
ISO 27001
certified
Deep Sea Tech Inc. — Made with ❤️ in Bangalore & San Francisco 🏢

Doctor Droid

MCP Server Integration

Signoz MCP Server Integration

Explore tools that let you query your Signoz instance in real time — pulling metrics, dashboards, and APM signals to speed up debugging and investigations.

What is the Signoz MCP Server?

The Signoz MCP Server lets you connect developer tools like Cursor or Claude Desktop to your Signoz instance. It's an open-source project maintained by DrDroid (not affiliated with Signoz), and allows you to query logs, dashboards, metrics, and more — making observability data directly accessible within your IDE or AI assistant.

Available Tools

ToolPurpose
test_connection
Ensures your endpoint and API key are valid, avoiding wasted execution cycles
fetch_dashboards
Helps suggest dashboards based on alert context and powers dashboard previews
fetch_dashboard_details
Useful for debugging layout or checking what metrics a panel uses
fetch_dashboard_data
Shows which metrics were spiking at the time of an alert
query_metrics
Core to automated diagnosis - detects sudden spikes or anomalies
fetch_apm_metrics
Essential for identifying service-level performance issues

Tool Details

Each tool represents a capability that can be invoked automatically during alert investigations or manually by engineers using Dr. Droid's AI assistant.
test_connection
Verifies that your Signoz instance is reachable and properly configured
Why it's useful
Ensures your endpoint and API key are valid, avoiding wasted execution cycles
Sample Output
{ "status": "ok", "message": "Connection successful" }
Use Cases
Validates connectivity before running debugging workflows
fetch_dashboards
Fetches a list of all dashboards available in your Signoz instance
Why it's useful
Helps suggest dashboards based on alert context and powers dashboard previews
Sample Output
[
 {
   "id": "payment-overview",
   "title": "Payment Service Overview",
   "tags": ["service:payments"]
 }
]

Use Cases
Used to suggest relevant dashboards during incident investigation
fetch_dashboard_details
Retrieves metadata for a dashboard by ID — includes panel configuration and query structure
Why it's useful
Useful for debugging layout or checking what metrics a panel uses
Sample Input
{ "dashboard_id": "payment-overview" }
Sample Output
{
 "dashboard": {
   "id": "payment-overview",
   "panels": [
     {
       "title": "Error Rate",
       "query": "rate(http_requests_total{status='500'}[5m])"
     }
   ]
 }
}

Use Cases
Validates connectivity before running debugging workflows
fetch_dashboard_data
Fetches live panel data from a dashboard for a given time range
Why it's useful
Shows which metrics were spiking at the time of an alert
Sample Input
{
 "dashboard_id": "payment-overview",
 "start": "now-15m",
 "end": "now"
}

Sample Output
{
 "dashboard": "payment-overview",
 "data": [
   {
     "panel": "Error Rate",
     "values": [
       { "timestamp": 1721010000, "value": 0.12 },
       { "timestamp": 1721010600, "value": 0.25 }
     ]
   }
 ]
}

Use Cases
Enables side-by-side panel comparisons in incident summaries
query_metrics
Executes a custom metric query over a specified time range
Why it's useful
Core to automated diagnosis - detects sudden spikes or anomalies
Sample Input
{
 "query": "rate(http_request_duration_seconds_sum[5m])",
 "start": "now-15m",
 "end": "now"
}

Sample Output
Time-series data for the requested metric
Use Cases
Used by AI to detect performance anomalies during alerts
fetch_apm_metrics
Fetches common APM metrics for a given service: Latency, Error Rate, Throughput, Apdex
Why it's useful
Essential for identifying service-level performance issues
Sample Input
{
 "service_name": "auth-service",
 "start": "now-15m",
 "end": "now"}

Sample Output
{
 "latency": "360ms",
 "error_rate": "3%",
 "throughput": "410 rpm",
 "apdex": "0.83"
}

Use Cases
Especially useful when multiple services are involved in an incident

Frequently Asked Questions

Is this an official Signoz project?
Which AI tools and IDEs are supported?
Do I need special permissions to use this with my Signoz instance?
Can I use this with Signoz Cloud?
Is my data secure?
How do I contribute to this project?

Ready to Get Started?

Visit our GitHub repository for detailed setup instructions and start integrating Signoz with your AI-powered observability workflows today.

SOC 2 Type II
certifed
ISO 27001
certified
Deep Sea Tech Inc. — Made with ❤️ in Bangalore & San Francisco 🏢

Doctor Droid

MCP Server Integration

Grafana MCP Server Integration

Explore tools that let you query your Grafana instance in real time — pulling metrics, logs, dashboards, and more to speed up debugging and investigations.

What is the Grafana MCP Server?

The Grafana MCP Server lets you connect developer tools like Cursor or Claude Desktop to your Grafana instance. It’s an open-source project maintained by DrDroid (not affiliated with Grafana), and it allows you to query metrics via PromQL, fetch dashboards, pull log data from Loki, and more — all directly from your IDE or AI assistant.

Available Tools

ToolPurpose
test_connection
Verifies connection to your Grafana instance and API configuration
grafana_promql_query
Executes PromQL queries over Prometheus data sources
grafana_loki_query
Queries logs from Grafana Loki
grafana_get_dashboard_config
Retrieves configuration metadata for a given dashboard
grafana_query_dashboard_panels
Queries data from up to 4 dashboard panels
grafana_fetch_label_values
Fetches available label values from Prometheus datasource
grafana_fetch_dashboard_variables
Retrieves template variables from a dashboard
grafana_fetch_all_dashboards
Lists all dashboards with title, UID, folder, and tags
grafana_fetch_datasources
Lists all configured Grafana data sources
grafana_fetch_folders
Fetches folder-level metadata and permissions

Tool Details

Each tool represents a capability that can be invoked automatically during alert investigations or manually by engineers using Dr. Droid's AI assistant.
test_connection
Verifies that your Grafana instance and API key are valid.
Why it's useful
Avoids wasted executions due to misconfiguration or invalid credentials.
Sample Output
{ "status": "ok", "message": "Connection successful" }
Use Cases
Validate Grafana connectivity before launching workflows.
grafana_promql_query
Executes PromQL queries over Grafana’s Prometheus datasource.
Why it's useful
Central to debugging infrastructure or service metrics — optimized for fast responses.
Sample Input
{  "query": "rate(http_requests_total[5m])",  "start": "now-15m",  "end": "now"}
Use Cases
Used in AI-powered workflows to detect CPU spikes, memory leaks, and more.
grafana_loki_query
Queries logs using Grafana Loki for a specified duration.
Why it's useful
Surface correlated log lines for alerts and incidents in a time-bounded manner.
Sample Input
{  "query": "{job=\"auth-service\"}",  "duration": "5m"}
Use Cases
Helps trace error patterns or recent logs during incidents.
grafana_get_dashboard_config
Fetches dashboard metadata including panel structure and queries.
Why it's useful
Understand how a dashboard is constructed — useful for debugging and suggestions.
Use Cases
Useful during alert triage to trace dashboards linked to services.
grafana_query_dashboard_panels
Executes data queries for specific dashboard panels (up to 4).
Why it's useful
Enables snapshotting of panels directly in investigations or summaries.
Use Cases
Used in incident timelines to show current metrics from key panels.
grafana_fetch_label_values
Retrieves label values (e.g., job, instance) from Prometheus datasource.
Why it's useful
Powers dynamic dashboards and filters in AI investigations.
grafana_fetch_dashboard_variables
Fetches template variables and their values from a dashboard.
Why it's useful
Required to execute parameterized panels and personalize responses.
grafana_fetch_all_dashboards
Lists all dashboards available in the instance.
Why it's useful
Helps suggest dashboards based on services, tags, or folder grouping.
grafana_fetch_datasources
Returns metadata about all data sources configured in Grafana.
Why it's useful
Important for validating where metrics or logs are sourced from.
grafana_fetch_folders
Lists all folders with permissions and metadata.
Why it's useful
Can be used to organize incident views or restrict access programmatically.

Frequently Asked Questions

Is this an official Grafana integration?
Which clients can use this?
What access is needed?
Does this support Grafana Cloud?
Is data sent to external servers?
How can I contribute?

Ready to Get Started?

Visit our GitHub repo for installation instructions and start connecting Grafana to your IDE or AI assistant in minutes.

SOC 2 Type II
certifed
ISO 27001
certified
Deep Sea Tech Inc. — Made with ❤️ in Bangalore & San Francisco 🏢

Doctor Droid