API & MCP - DataFramer

Getting access

Register at app.dataframer.ai
Request access to Dataframer at [email protected]
Get your API key from the dashboard (Settings → API Keys)
Set the environment variable:

export DATAFRAMER_API_KEY="your-api-key"

Python SDK

Install the SDK:

pip install pydataframer

Quick taste:

from dataframer import Dataframer

client = Dataframer()  # uses DATAFRAMER_API_KEY env var

spec = client.dataframer.specs.create(
    name="Customer Support Tickets",
    generation_objectives="Generate realistic customer support tickets...",
)
# ... poll for completion, start a run, download results

See the Basic Use of Python SDK tutorial for a complete, runnable example.

MCP

MCP lets AI assistants (Claude Code, Cursor, etc.) interact with DataFramer directly.

Claude Code

claude mcp add --transport http \
  --header "Authorization: Bearer $DATAFRAMER_API_KEY" \
  --scope user dataframer https://df-api.dataframer.ai/mcp

Unlike the raw API, MCP also provides your AI assistant with detailed instructions on how to use DataFramer effectively — so it can guide you through the entire workflow conversationally.

Next steps

Core Concepts

Understand how DataFramer works

Basic Use of Python SDK

Complete runnable example

API Reference

Full endpoint documentation

Complete Generation Guide Data Anonymization

​Getting access

​Python SDK

​MCP

​Claude Code

​Next steps