Tibber

You can run a Tibber MCP Server locally to let an AI agent query Tibber’s API for current energy prices, consumption data, and related insights. It’s designed to be run alongside MCP clients so you can interact with energy information through natural language prompts and practical questions.

How to use

After you start the Tibber MCP Server, you connect your MCP client (such as Claude Desktop or Roo Code) and begin asking questions about your energy data. Useful queries include checking current energy prices, reviewing yesterday’s consumption, identifying peak usage times, and finding the cheapest hours for tomorrow. You can have the AI agent analyze your data and present patterns like typical peak periods or notable consumption spikes in an easy-to-understand format.

In your MCP client, select the Tibber MCP Server configuration and run the server. The server exposes tools to fetch consumption data and price/home information, enabling you to compose increasingly complex requests that combine data points (for example, comparing yesterday’s price vs. today or listing the top three cheapest hours for tomorrow).

How to install

Prerequisites you need to prepare before you start:

• Python 3.12 installed on your machine

• A Tibber API token from the Tibber developer portal

Follow these steps to set up and run the Tibber MCP Server locally:

# 1) Install uv (cross-platform utility for MCP runtimes)
curl -LsSf https://astral.sh/uv/install.sh | sh
# or on Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

# 2) Clone this Tibber MCP project and enter the folder
git clone https://github.com/linkcd/tibber-mcp.git
cd tibber-mcp

# 3) Set up the Python virtual environment and install dependencies
uv venv --python 3.12
source .venv/bin/activate
uv pip install --requirement pyproject.toml

Host configuration for MCP clients

Configure your MCP client to run the Tibber MCP Server as a local process. The following configuration uses uv to start the server from the root of the cloned project and passes your Tibber API token securely via environment variables.

{
  "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]"
      }
    }
  }
}

Available tools

get_consumption_data

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

get_price_and_home_info

Fetch current, today, and tomorrow energy prices plus home information (owner, address, subscription, etc.).