Tibber

You run a Tibber MCP Server to securely access Tibber energy data from an MCP client. It lets an AI agent ask questions about current energy prices, yesterday’s consumption, and other energy insights by connecting to Tibber through a simple MCP interface.

How to use

Connect your MCP client to the Tibber MCP Server using the stdio configuration described in the host setup. Once connected, you can ask questions like the following to quickly get actionable energy insights: the current energy price, yesterday’s total consumption, the hourly consumption pattern over the last 30 days, or the cheapest hours for tomorrow.

Typical usage patterns include: asking for a summary of peak consumption periods, finding when you used the most power yesterday, requesting the total energy consumed at a specific time, and comparing tomorrow’s energy price against today. Your MCP client can also fetch the current price and home information such as the owner and address when supported.

For local development and testing, provide your Tibber API token to the server environment and run the server in a way that your MCP client can reach. You can also debug with an inspector tool by passing your token to evaluate the server interactions during development.

How to install

Prerequisites you need before starting: Python 3.12 and a Tibber API token obtained from the Tibber developer portal.

# On macOS and Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# On Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Clone the Tibber MCP Server repository and enter the project folder.

git clone https://github.com/linkcd/tibber-mcp.git
cd tibber-mcp

Create and activate a Python virtual environment and install dependencies from the project configuration.

uv venv --python 3.12 && source .venv/bin/activate && uv pip install --requirement pyproject.toml

Configure the MCP host to run the Tibber server locally. Use your Tibber API token in the environment. The following configuration runs the server script from the root of the cloned folder.

{
  "mcpServers":{
    "tibber":{
      "command":"uv",
      "args":[
        "--directory",
        "[PATH-TO-ROOT-OF-THE-CLONED-TIBBER-MCP-FOLDER]",
        "run",
        "server.py"
      ],
      "env":{
        "TIBBER_API_TOKEN":"[YOUR-TIBBER-TOKEN]"
      }
    }
  }
}

If you want to test quickly without a full MCP client setup, you can start the server directly (replace tokens as needed) and verify basic responses with a compatible inspector tool.

Additional notes

Environment variables shown for the MCP setup must be kept secure and never committed to version control. The Tibber API token is required to fetch price and consumption data.

The server exposes two primary capabilities you can leverage from your MCP client: fetch consumption data for the last 30 days and fetch current/today/tomorrow price information plus home details.

Development and debugging can be performed with an inspector to ensure the MCP client sees the expected data endpoints and responses during development.

Troubleshooting and tips

If you encounter token-related errors, regenerate your Tibber API token from the Tibber developer portal and update the TIBBER_API_TOKEN value in your environment. Ensure the token is available to the process running the MCP server.

Verify the server process starts with the correct working directory and that the path to server.py matches your cloned project layout. Check that the uv tool is installed and accessible in your environment.

Available tools

get_consumption_data

Retrieves hourly consumption data for the last 30 days, including time period, total cost, base energy cost, and consumed kWh.

get_price_and_home_info

Fetches current, today, and tomorrow price information along with basic home details such as owner and address.