Grafana MCP Server

Search for dashboards by title, tags, or other metadata

Get full dashboard details using its unique identifier

Update an existing dashboard or create a new one. Use with caution due to context window limitations.

Get the title, query string, and datasource information from every panel in a dashboard

Get version history for a dashboard

Restore a dashboard to a specific version

Delete a dashboard by UID

List all teams in the organization

Get team details by UID

List all users in the organization

Get current user information

List all folders

Get folder details by UID

List all API keys

List all service accounts

Get current organization information

List all configured datasources with their details

Get detailed information about a datasource using its UID

Get detailed information about a datasource using its name

Test the connection to a datasource by UID

Get all datasources of a specific type (e.g., prometheus, loki, mysql)

Get the default datasource for the organization

Check if a datasource exists by UID or name

Execute a PromQL query against a Prometheus datasource

Get metadata for all metrics from a Prometheus datasource

Get all label names from a Prometheus datasource

Get all values for a specific label from a Prometheus datasource

Find series matching label matchers from a Prometheus datasource

Help build a Prometheus query with suggestions for metric names and operators

Execute a LogQL query against a Loki datasource to search logs

Get all label names available in a Loki datasource

Get all values for a specific label in a Loki datasource

Get series (label combinations) matching label selectors from a Loki datasource

Help build a LogQL query with suggestions for log stream selectors and filters

Get statistics about ingestion and query performance from a Loki datasource

List all alert rules in Grafana

Get detailed information about a specific alert rule

Create a new alert rule

Update an existing alert rule

Delete an alert rule by UID

List all notification contact points

Get detailed information about a specific contact point

Send a test notification to a contact point

List all alert rule groups

Generate a deeplink URL for Grafana dashboards, panels, or explore view

Generate a URL for a specific dashboard with optional time range and variables

Generate a URL for a specific panel with optional time range

Generate a URL for the Explore view with optional datasource and query

Generate an Explore URL for Prometheus queries with specific options

Generate an Explore URL for Loki log queries

Get common time range presets for Grafana

Validate a time range for Grafana usage

Scan ports for active SSH-tunneled Corelight sensor Grafana instances. Returns connected sensors with hostname, port, Grafana version, and Prometheus status.

Get live performance snapshot for a sensor: Gbps, kpps, klogps, drop rates, max worker CPU, buffer utilization, and system memory. Uses 5-min rate smoothing.

Execute arbitrary PromQL against a sensor's Prometheus datasource. Auto-resolves datasource UID and target sensor.

Deploy the RAMP Performance Analysis dashboard to a sensor's Grafana. Optionally patch with baseline comparison panels by specifying a build and profile.

List available builds and profiles from baselines.json. Optionally filter by sensor type (e.g., "AP1100", "AP3000").

Compare live sensor metrics against a baseline build and return a structured verdict. Thresholds: <5% = PASS, 5-10% = MINOR REGRESSION (P2), >10% = MAJOR REGRESSION (P1), any drops = FAIL.

Add a Grafana annotation on a sensor for test events (start/end/result/rate change). Supports range annotations and dashboard association. Tagged with ramp-test by default.

Run performance verdict against all discovered sensors in parallel. Returns per-sensor results and fleet summary.

Show a sensor type's performance across all builds in baselines.json. Useful for spotting when regressions were introduced.

List RAMP test runs from the results directory. Filter by date or sensor name.

Read the final result (Gbps, kpps, klogps, status) from a RAMP test run.

Read all VITAL metric samples from a RAMP test run (time-series data).

Get a complete summary of a RAMP test run including metadata, final result, vital count, and error status.

Run a comprehensive diagnostic battery against a sensor to identify where drops are occurring and why. Returns drop sources by layer (NIC/Zeek/Suricata), bottleneck classification, and leading indicators.

Combine performance verdict with live diagnostic data to fingerprint the root cause of a regression.

Compare two firmware builds across all sensor types and profiles using baseline data.

Monitor a sensor during a RAMP test, polling metrics at a configurable interval.

List all available Prometheus metric names on a sensor, grouped by subsystem.

Set the Ixia traffic replayer to a specific rate in Gbps. This stops any running test and restarts at the new rate.

Stop the Ixia traffic replayer. Halts all traffic generation on the specified replayer.

Check the current status of an Ixia traffic replayer (running/stopped, rate, test model).

Start a RAMP performance test on the RAMP server. Set confirm=true to actually start; default is a dry run that shows what would run.

Stop a running RAMP test by killing its tmux session on the RAMP server.

Check the status of RAMP tests running on the RAMP server (lists active tmux sessions).

Run a regression sweep across all discovered sensors against a specific build. Checks each sensor against all its baseline profiles and optionally fingerprints regressions.

Extrapolate the maximum sustainable traffic rate for a sensor based on current resource utilization. Shows headroom per subsystem (Zeek CPU, buffer, memory) and identifies the limiting factor.

Assess whether a sensor is ready for a RAMP test by checking for existing drops, memory pressure, CPU baseline, and buffer residue. Returns a risk score and go/no-go recommendation.

Analyze historical baseline data to predict how the next firmware build will affect performance. Shows trend direction (improving/stable/declining) per sensor type and profile, with fleet-wide risk.