> Forked from Grafana MCP server

This repository is a fork of the original Grafana MCP server.

It includes custom modifications listed below.

Changes from upstream

• Added support for a new tool: QuestDB
  • Introduced `questdb` flag to enable/disable
  • Added `tools/questdb.go` implementing the QuestDB query logic
• Added support for a new tool: Athena
  • Introduced `athena` flag to enable/disable
  • Added `tools/athena.go` implementing the Athena query logic
• Extended transport options to support `streamable-http`
• Added dependency: `github.com/DataDog/zstd`

Grafana MCP server

A [Model Context Protocol][mcp] (MCP) server for Grafana.

This provides access to your Grafana instance and the surrounding ecosystem.

Features

_The following features are currently available in MCP server. This list is for informational purposes only and does not represent a roadmap or commitment to future features._

Dashboards

• Search for dashboards: Find dashboards by title or other metadata
• Get dashboard by UID: Retrieve full dashboard details using its unique identifier
• Update or create a dashboard: Modify existing dashboards or create new ones. _Note: Use with caution due to context window limitations; see issue #101_
• Get panel queries and datasource info: Get the title, query string, and datasource information (including UID and type, if available) from every panel in a dashboard

Datasources

• List and fetch datasource information: View all configured datasources and retrieve detailed information about each.

Prometheus Querying

• Query Prometheus: Execute PromQL queries (supports both instant and range metric queries) against Prometheus datasources.
• Query Prometheus metadata: Retrieve metric metadata, metric names, label names, and label values from Prometheus datasources.

Loki Querying

• Query Loki logs and metrics: Run both log queries and metric queries using LogQL against Loki datasources.
• Query Loki metadata: Retrieve label names, label values, and stream statistics from Loki datasources.

Incidents

• Search, create, update, and close incidents: Manage incidents in Grafana Incident, including searching, creating, updating, and resolving incidents.

Sift Investigations

• Create Sift investigations: Start a new Sift investigation for analyzing logs or traces.
• List Sift investigations: Retrieve a list of Sift investigations, with support for a limit parameter.
• Get Sift investigation: Retrieve details of a specific Sift investigation by its UUID.
• Get Sift analyses: Retrieve a specific analysis from a Sift investigation.
• Find error patterns in logs: Detect elevated error patterns in Loki logs using Sift.
• Find slow requests: Detect slow requests using Sift (Tempo).

Alerting

• List and fetch alert rule information: View alert rules and their statuses (firing/normal/error/etc.) in Grafana.
• List contact points: View configured notification contact points in Grafana.

Grafana OnCall

• List and manage schedules: View and manage on-call schedules in Grafana OnCall.
• Get shift details: Retrieve detailed information about specific on-call shifts.
• Get current on-call users: See which users are currently on call for a schedule.
• List teams and users: View all OnCall teams and users.

Admin

• List teams: View all configured teams in Grafana.

The list of tools is configurable, so you can choose which tools you want to make available to the MCP client.

This is useful if you don't use certain functionality or if you don't want to take up too much of the context window.

To disable a category of tools, use the `--disable-` flag when starting the server. For example, to disable

the OnCall tools, use `--disable-oncall`.

Tools

Usage

1. Create a service account in Grafana with enough permissions to use the tools you want to use,

generate a service account token, and copy it to the clipboard for use in the configuration file.

Follow the [Grafana documentation][service-account] for details.

2. You have several options to install `mcp-grafana`:

Important: The Docker image's entrypoint is configured to run the MCP server in SSE mode by default, but most users will want to use STDIO mode for direct integration with AI assistants like Claude Desktop:

1. STDIO Mode: For stdio mode you must explicitly override the default with `-t stdio` and include the `-i` flag to keep stdin open:

docker pull mcp/grafana
     docker run --rm -i -e GRAFANA_URL=http://localhost:3000 -e GRAFANA_API_KEY= mcp/grafana -t stdio

2. SSE Mode: In this mode, the server runs as an HTTP server that clients connect to. You must expose port 8000 using the `-p` flag:

docker pull mcp/grafana
     docker run --rm -p 8000:8000 -e GRAFANA_URL=http://localhost:3000 -e GRAFANA_API_KEY= mcp/grafana

3. Streamable HTTP Mode: In this mode, the server operates as an independent process that can handle multiple client connections. You must expose port 8000 using the `-p` flag: For this mode you must explicitly override the default with `-t streamable-http`

docker pull mcp/grafana
     docker run --rm -p 8000:8000 -e GRAFANA_URL=http://localhost:3000 -e GRAFANA_API_KEY= mcp/grafana -t streamable-http

to specify the directory where the binary should be installed. This should also be in your `PATH`.

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

3. Add the server configuration to your client configuration file. For example, for Claude Desktop:

If using the binary:

{
     "mcpServers": {
       "grafana": {
         "command": "mcp-grafana",
         "args": [],
         "env": {
           "GRAFANA_URL": "http://localhost:3000",
           "GRAFANA_API_KEY": ""
         }
       }
     }
   }

> Note: if you see `Error: spawn mcp-grafana ENOENT` in Claude Desktop, you need to specify the full path to `mcp-grafana`.

If using Docker:

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

> Note: The `-t stdio` argument is essential here because it overrides the default SSE mode in the Docker image.

Using VSCode with remote MCP server

If you're using VSCode and running the MCP server in SSE mode (which is the default when using the Docker image without overriding the transport), make sure your `.vscode/settings.json` includes the following:

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

Debug Mode

You can enable debug mode for the Grafana transport by adding the `-debug` flag to the command. This will provide detailed logging of HTTP requests and responses between the MCP server and the Grafana API, which can be helpful for troubleshooting.

To use debug mode with the Claude Desktop configuration, update your config as follows:

If using the binary:

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

If using Docker:

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

> Note: As with the standard configuration, the `-t stdio` argument is required to override the default SSE mode in the Docker image.

Development

Contributions are welcome! Please open an issue or submit a pull request if you have any suggestions or improvements.

This project is written in Go. Install Go following the instructions for your platform.

To run the server locally in STDIO mode (which is the default for local development), use:

make run

To run the server locally in SSE mode, use:

go run ./cmd/mcp-grafana --transport sse

You can also run the server using the SSE transport inside a custom built Docker image. Just like the published Docker image, this custom image's entrypoint defaults to SSE mode. To build the image, use:

make build-image

And to run the image in SSE mode (the default), use:

docker run -it --rm -p 8000:8000 mcp-grafana:latest

If you need to run it in STDIO mode instead, override the transport setting:

docker run -it --rm mcp-grafana:latest -t stdio

Testing

There are three types of tests available:

1. Unit Tests (no external dependencies required):

make test-unit

You can also run unit tests with:

make test

2. Integration Tests (requires docker containers to be up and running):

make test-integration

3. Cloud Tests (requires cloud Grafana instance and credentials):

make test-cloud

> Note: Cloud tests are automatically configured in CI. For local development, you'll need to set up your own Grafana Cloud instance and credentials.

More comprehensive integration tests will require a Grafana instance to be running locally on port 3000; you can start one with Docker Compose:

docker-compose up -d

The integration tests can be run with:

make test-all

If you're adding more tools, please add integration tests for them. The existing tests should be a good starting point.

Linting

To lint the code, run:

make lint

This includes a custom linter that checks for unescaped commas in `jsonschema` struct tags. The commas in `description` fields must be escaped with `\\,` to prevent silent truncation. You can run just this linter with:

make lint-jsonschema

See the JSONSchema Linter documentation for more details.

License

This project is licensed under the Apache License, Version 2.0.

[mcp]: https://modelcontextprotocol.io/

[service-account]: https://grafana.com/docs/grafana/latest/administration/service-accounts/