~
$ pip install dante-ds[postgres]
Successfully installed dante-ds-0.1.0
$ claude "what were our top customers last quarter?"
dante Querying analytics.customers... found 2,847 rows
dante Building visualization...
dante Top 10 customers by revenue (Q4 2025):
  1. Acme Corp — $2.4M
  2. Globex — $1.8M
  3. Initech — $1.2M
  ... rendered chart to output.html

# Turn Claude Code into a
data science workbench.

dante-ds is an MCP server that gives Claude direct access to your databases. Ask questions in plain English, get SQL, charts, and analysis — without leaving your terminal.

pypiv0.1.0
python3.10+
licenseMIT
protocolMCP
$ pip install dante-ds

// how_it_works

Three steps from zero to querying your production database inside Claude Code.

1

Install the package

Pick your database extras: pip install dante-ds[postgres,snowflake]

2

Add the MCP server

Register dante-ds in your Claude Code settings. Point it at your connection string.

3

Start asking questions

"What were our top 10 customers by revenue last quarter?" — Claude writes the SQL, runs it, returns the results.

// features

Everything Claude needs to be your data science co-pilot.

MCP Server

Runs as a Model Context Protocol server. Claude Code discovers database tools automatically — no prompt engineering required.

Python stdio transport

Multi-Database

PostgreSQL, Snowflake, BigQuery, Databricks, MySQL. Install only the drivers you need with optional extras.

SQL 8 adapters

Plotly Charts

Claude generates interactive Plotly visualizations from query results. Bar charts, scatter plots, time series — rendered inline.

Python plotly.js

Schema Discovery

Automatically inspects tables, columns, types, and foreign keys. Claude understands your data model before writing a single query.

SQL introspection

Read-Only by Default

All queries run as SELECT statements with row limits. Your production data stays safe — no accidental writes or deletes.

SELECT only row limits

Looker Integration

Browse Looker dashboards and explores directly from Claude. Pull existing SQL patterns into your analysis.

Looker API LookML

// quick_start

Install, configure, and start querying.

terminal
# core package
$ pip install dante-ds

# with database drivers
$ pip install dante-ds[postgres]
$ pip install dante-ds[snowflake,bigquery]
$ pip install dante-ds[all]
.claude/settings.json
{
  "mcpServers": {
    "dante": {
      "command": "dante-ds",
      "args": ["serve"],
      "env": {
        "DATABASE_URL": "postgresql://..."
      }
    }
  }
}

// supported_databases

Install only the drivers you need. Each database is an optional extra.

PostgreSQL Snowflake BigQuery Databricks MySQL Looker DuckDB Parquet

Data science at the speed of thought.

Stop context-switching between your editor and a SQL client. Let Claude handle the queries.

dante studio
user show me revenue by region for Q4
dante Querying warehouse.orders... 14,203 rows
dante Generating bar chart...
dante Built data app: "Q4 Revenue by Region"
  Published to /app/q4-revenue
  4 KPI cards, 2 charts, 1 filter
  Share: https://dantefordata.com/app/q4-revenue

# Ask questions.
Get dashboards.

Dante Studio turns natural language into live, interactive data apps. Connect your warehouse, chat with your data, and publish reports your leadership team will actually read.

statuslive
authGoogle OAuth
aiClaude
stackReact + FastAPI

// how_it_works

From question to published report in minutes. No SQL required.

1

Connect your data

Point Dante at your Postgres warehouse, Databricks, Looker, or local Parquet files.

2

Ask in plain English

"Show me revenue by region for Q4" — the AI agent writes and executes the SQL for you.

3

Build a data app

One click turns your analysis into an interactive dashboard with charts, KPIs, and filters.

4

Publish and share

Get a clean URL like /app/q4-revenue and send it to your stakeholders.

// features

A complete analytics platform — from raw SQL to polished, live dashboards.

Conversational Analytics

Chat with an AI agent that writes SQL, runs Python, and builds visualizations. Powered by Claude with streaming responses.

TypeScript Claude Agent SDK

Interactive Data Apps

Build dashboards from templates — KPI cards, chart grids, map explorers. AI generates the HTML, CSS, and JS.

React live preview

Notebooks

Jupyter-style computational notebooks with a multi-step analysis pipeline. Code cells execute in isolated kernels.

Python sandboxed

Shareable Reports

Publish data apps with clean vanity URLs. Set visibility to public or org-only. Lock reports to prevent edits.

vanity URLs access control

Knowledge Base

Build a library of notes, keywords, and SQL embeddings. The AI uses vector search to get smarter with every query.

pgvector RAG

Enterprise Ready

Google OAuth, role-based access, encrypted credentials, per-user token budgets, and full usage tracking.

OAuth 2.0 RBAC

// integrations

Bring your own data. Studio reads from your warehouse and BI tools — nothing to migrate.

PostgreSQL Databricks Looker DuckDB Parquet Snowflake BigQuery MCP Servers

Stop writing dashboards. Start shipping them.

Get from raw data to published report faster than your team can schedule a meeting about it.