Grafana MCP server for AI agents

The Grafana MCP server provides a Model Context Protocol interface to interact with your Grafana instance and ecosystem. It allows AI assistants to query metrics, visualize data, and manage dashboards through a standardized API.

Installation Options

Using Docker Image

The Docker image is pre-configured to run in SSE mode, but you can override it for different usage scenarios:

STDIO Mode (for Claude Desktop integration)

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

SSE Mode (HTTP server that clients connect to)

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

Streamable HTTP Mode (independent process for multiple clients)

docker pull mcp/grafana
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 releases page and place it in your $PATH.

Build from Source

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

Configuration

Client Setup for Claude Desktop

Using the Binary:

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

Using Docker:

{
  "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": "<your-token>"
      }
    }
  }
}

VSCode with Remote MCP Server

"mcp": {
  "servers": {
    "grafana": {
      "type": "sse",
      "url": "http://localhost:8000/sse"
    }
  }
}

Available Features

Dashboards

Search for dashboards
Get dashboard by UID
Get dashboard summary
Extract specific dashboard properties
Update or create dashboards
Get panel queries and datasource info

Datasources

List and fetch datasource information

Querying

Execute PromQL against Prometheus datasources
Query metadata, metric names, and labels
Query Loki logs and metrics
Retrieve Loki metadata

Alerting

List alert rules and statuses
List contact points

Incidents

Search, create, and update incidents

Admin

List teams and users

Navigation

Generate deeplinks to Grafana resources

Advanced Configuration

Debug Mode

Enable debug mode to troubleshoot issues:

mcp-grafana -debug

TLS Configuration

For secure connections to Grafana:

mcp-grafana --tls-cert-file /path/to/client.crt --tls-key-file /path/to/client.key --tls-ca-file /path/to/ca.crt

Server TLS (Streamable HTTP only)

mcp-grafana -t streamable-http --server.tls-cert-file /path/to/server.crt --server.tls-key-file /path/to/server.key -addr :8443

Disabling Features

You can disable specific features to reduce context window usage:

mcp-grafana --disable-incident --disable-oncall

Troubleshooting

If you encounter datasource-related errors like:

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

This typically indicates you're using Grafana version earlier than 9.0. Upgrade to Grafana 9.0 or later.

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