Install Tabsdata
Deploy a Tabsdata Server on your Machine in under 5 minutes.
Tabsdata is published as a python package, installable with pip
- Machine with a supported OS
- Linux (x86)
- macOS (Apple Silicon/ARM64)
- Windows (x86)
- Python 3.12
- An LLM API key from Anthropic or OpenAI (Required for AI features)
Set LLM key as environment variable in terminal
- macOS / Linux
- Windows (PowerShell)
export ANTHROPIC_KEY="sk-ant-..."
$env:ANTHROPIC_KEY = "sk-ant-..."
Create a Python virtual environment
Using a virtual environment provides a layer of isolation and prevents interference from other python environments on your machine.
- macOS / Linux
- Windows (PowerShell)
- conda
- uv
- pyenv
- venv
conda create -n tabsdata python=3.12 -y
conda activate tabsdata
uv venv --python 3.12 .venv
source .venv/bin/activate
pyenv install 3.12
pyenv local 3.12
python -m venv .venv
source .venv/bin/activate
python3 -m venv .venv
source .venv/bin/activate
- conda
- uv
- pyenv
- venv
conda create -n tabsdata python=3.12 -y
conda activate tabsdata
uv venv --python 3.12 .venv
.venv\Scripts\activate
pyenv install 3.12
pyenv local 3.12
python -m venv .venv
.venv\Scripts\activate
python -m venv .venv
.venv\Scripts\activate
Install Tabsdata
pip install "tabsdata[all]"
Start the Tabsdata server
tdkserver quickstart initializes and deploys a Tabsdata Instance. The command should take around 30 seconds to fully execute.
- Anthropic
- OpenAI
tdkserver quickstart --anthropic-key $ANTHROPIC_KEY
tdkserver quickstart --openai-key $OPENAI_KEY
Check Tabsdata server status
View all your Tabsdata Instances
tdkserver list
View the status of the Tabsdata Instance you just deployed.
tdkserver status
tdkserver commands usually require an --instance flag that specifies the specific instance you want to interact with. If no --instance flag is passed, Tabsdata defaults the instance name to tabsdata
Log in
tdk login --server localhost --user admin --password tabsdata
Or access the UI at http://localhost:2457/login
Next: Connect an AI Agent. Point your LLM at the MCP server, then run your first pipeline.