Skip to main content
Glama
tamalkarm

Grafana Context MCP

by tamalkarm

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GRAFANA_URLYesThe base URL of the Grafana instance, e.g. https://grafana.example.com
GRAFANA_ORG_IDNoOptional Grafana organization ID
GRAFANA_VERIFY_SSLNoWhether to verify TLS certificates for Grafana connectionstrue
GRAFANA_TIMEOUT_SECONDSNoTimeout for Grafana API requests in seconds30
GRAFANA_SERVICE_ACCOUNT_TOKENYesGrafana service account token with read-only permissions

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_datasourcesA

List configured data sources without exposing stored credentials.

get_datasourceA

Get configuration metadata for one data source by UID.

check_datasource_healthA

Run the Grafana plugin health check for one data source.

search_dashboardsA

Search dashboards by title and optional tag.

get_dashboardA

Get the complete dashboard JSON and metadata.

analyze_dashboardA

Explain dashboard structure, queries, data sources, variables, semantics, and interpretation risks.

query_datasourceA

Run bounded, read-only native plugin queries through Grafana's data source query API.

Prompts

Interactive templates invoked by user choice

NameDescription
investigate_dashboardGuide a careful, evidence-based dashboard investigation.
troubleshoot_datasourceGuide data source connectivity and query troubleshooting.
explain_panelExplain the meaning and limitations of one dashboard panel.

Resources

Contextual data attached and managed by the client

NameDescription
datasource_guideReference for Grafana data source types and safe communication patterns.
dashboard_guideReference for reading dashboards and interpreting what panels mean.
querying_guideGuide to querying data sources through Grafana.
instance_datasourcesLive data source inventory from the configured Grafana instance.

TDQS

A4.1/5.0

Scored across 7 tools

Disambiguation5/5

Each tool has a clear and distinct responsibility: listing vs. getting vs. health-checking datasources, searching vs. getting vs. analyzing dashboards, and running queries. There is no meaningful overlap between tools that would cause an agent to select the wrong one.

Naming Consistency5/5

All tools follow the same verb_noun snake_case pattern (e.g., list_datasources, get_dashboard, analyze_dashboard, query_datasource). Naming is predictable and makes the toolset easy to navigate.

Tool Count5/5

Seven tools is a well-scoped size for a Grafana context server. Each tool covers a distinct, necessary operation without bloat or redundancy.

Completeness5/5

The toolset covers the full read-only context workflow: discovering datasources, checking their health, finding dashboards, retrieving dashboard JSON, understanding dashboard structure, and querying datasources. For the stated purpose of providing Grafana context, there are no significant gaps.

Maintenance

ActivityMaintained
ResponsivenessNo issues