API & MCP

Getting access

Sign up for free at app.dataframer.ai
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

Example:

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 --scope user dataframer https://mcp.dataframer.ai/mcp

Then run /mcp in Claude Code and sign in with your DataFramer account in the browser window that opens. MCP uses that sign-in, not the API key. Unlike the API, MCP also gives your AI assistant instructions on how to use DataFramer, so the assistant can walk you through the workflow in chat.

Next steps

Core Concepts

Understand how DataFramer works

Basic Use of Python SDK

Complete runnable example

API Reference

Full endpoint documentation

Get started

Capture & Correlate

User Journeys & AI

Findings

Human review operations

Judges and Evaluations

Data Generation

Integrations

Programmatic Access

Getting access

Python SDK

MCP

Claude Code

Next steps

Core Concepts

Basic Use of Python SDK

API Reference

​Getting access

​Python SDK

​MCP

​Claude Code

​Next steps

Core Concepts

Basic Use of Python SDK

API Reference

Getting access

Python SDK

MCP

Claude Code

Next steps