Grafana MCP server for AI agents

The Grafana MCP server is a powerful interface that provides programmatic access to your Grafana instance and its ecosystem through the Model Context Protocol (MCP). It allows you to query dashboards, datasources, metrics, logs, and other Grafana resources.

Installation Options

You have several ways to install the MCP server:

Docker Image (Recommended)

Pull the pre-built Docker image from Docker Hub:

docker pull mcp/grafana

For direct integration with AI assistants (STDIO mode):

docker run --rm -i \
  -e GRAFANA_URL=http://localhost:3000 \
  -e GRAFANA_SERVICE_ACCOUNT_TOKEN=<your-token> \
  mcp/grafana -t stdio

For SSE mode (HTTP server that clients connect to):

docker run --rm -p 8000:8000 \
  -e GRAFANA_URL=http://localhost:3000 \
  -e GRAFANA_SERVICE_ACCOUNT_TOKEN=<your-token> \
  mcp/grafana

For streamable HTTP mode (handles multiple client connections):

docker run --rm -p 8000:8000 \
  -e GRAFANA_URL=http://localhost:3000 \
  -e GRAFANA_SERVICE_ACCOUNT_TOKEN=<your-token> \
  mcp/grafana -t streamable-http

Download Binary

Download the latest release from the GitHub releases page and place it in your $PATH.

Build from Source

If you have Go installed:

GOBIN="$HOME/go/bin" go install github.com/grafana/mcp-grafana/cmd/mcp-grafana@latest

Deploy to Kubernetes using Helm

helm repo add grafana https://grafana.github.io/helm-charts
helm install --set grafana.apiKey=<Grafana_ApiKey> --set grafana.url=<GrafanaUrl> my-release grafana/grafana-mcp

Configuration

Authentication

Create a service account in Grafana with appropriate permissions and generate a token:

{
  "mcpServers": {
    "grafana": {
      "command": "mcp-grafana",
      "args": [],
      "env": {
        "GRAFANA_URL": "http://localhost:3000",
        "GRAFANA_SERVICE_ACCOUNT_TOKEN": "<your-token>"
      }
    }
  }
}

You can also use username/password authentication:

{
  "mcpServers": {
    "grafana": {
      "command": "mcp-grafana",
      "args": [],
      "env": {
        "GRAFANA_URL": "http://localhost:3000",
        "GRAFANA_USERNAME": "<username>",
        "GRAFANA_PASSWORD": "<password>"
      }
    }
  }
}

Multi-Organization Support

To specify which organization to interact with:

{
  "mcpServers": {
    "grafana": {
      "command": "mcp-grafana",
      "args": [],
      "env": {
        "GRAFANA_URL": "http://localhost:3000",
        "GRAFANA_SERVICE_ACCOUNT_TOKEN": "<token>",
        "GRAFANA_ORG_ID": "2"
      }
    }
  }
}

Docker Configuration Example

{
  "mcpServers": {
    "grafana": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "GRAFANA_URL",
        "-e",
        "GRAFANA_SERVICE_ACCOUNT_TOKEN",
        "mcp/grafana",
        "-t",
        "stdio"
      ],
      "env": {
        "GRAFANA_URL": "http://localhost:3000",
        "GRAFANA_SERVICE_ACCOUNT_TOKEN": "<token>"
      }
    }
  }
}

Advanced Configuration

Debug Mode

Enable detailed logging for troubleshooting:

{
  "mcpServers": {
    "grafana": {
      "command": "mcp-grafana",
      "args": ["-debug"],
      "env": {
        "GRAFANA_URL": "http://localhost:3000",
        "GRAFANA_SERVICE_ACCOUNT_TOKEN": "<token>"
      }
    }
  }
}

TLS Configuration

For Grafana instances requiring client certificates or custom CA:

{
  "mcpServers": {
    "grafana": {
      "command": "mcp-grafana",
      "args": [
        "--tls-cert-file",
        "/path/to/client.crt",
        "--tls-key-file",
        "/path/to/client.key",
        "--tls-ca-file",
        "/path/to/ca.crt"
      ],
      "env": {
        "GRAFANA_URL": "https://secure-grafana.example.com",
        "GRAFANA_SERVICE_ACCOUNT_TOKEN": "<token>"
      }
    }
  }
}

Tool Configuration

You can selectively enable or disable specific tool categories:

mcp-grafana --enabled-tools "search,dashboard,prometheus,loki" --disable-write

The --disable-write flag provides read-only mode, preventing any modifications to your Grafana instance.

Features and Capabilities

The MCP server provides access to various Grafana features:

Dashboard Management

Search for dashboards
Get dashboard details (full JSON or summarized views)
Extract specific dashboard properties
Update or create dashboards
Get panel queries and datasource information

Datasource Operations

List all datasources
Get datasource details by UID or name

Prometheus Querying

Execute PromQL queries
Get metric metadata, names, labels, and values

Loki Log Analysis

Query logs using LogQL
Get label names and values
Retrieve stream statistics

Alerting

List alert rules and their statuses
View contact points for notifications

Incident Management

Search, create, and update incidents
Add activities to incidents

Grafana OnCall

Manage on-call schedules and shifts
View current on-call users
List teams, users, and alert groups

Navigation

Generate accurate deeplinks to Grafana resources

Troubleshooting

If you encounter datasource-related errors like:

get datasource by uid : [GET /datasources/uid/{uid}][400] getDataSourceByUidBadRequest {"message":"id is invalid"}

This indicates that your Grafana version is older than 9.0. Upgrade to Grafana 9.0 or later to resolve this issue.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "grafana" '{"command":"mcp-grafana","args":[],"env":{"GRAFANA_URL":"http://localhost:3000","GRAFANA_API_KEY":"<your service account token>"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "grafana": {
            "command": "mcp-grafana",
            "args": [],
            "env": {
                "GRAFANA_URL": "http://localhost:3000",
                "GRAFANA_API_KEY": "<your service account token>"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "grafana": {
            "command": "mcp-grafana",
            "args": [],
            "env": {
                "GRAFANA_URL": "http://localhost:3000",
                "GRAFANA_API_KEY": "<your service account token>"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect