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.
pip install dante-ds
Three steps from zero to querying your production database inside Claude Code.
Pick your database extras: pip install dante-ds[postgres,snowflake]
Register dante-ds in your Claude Code settings. Point it at your connection string.
"What were our top 10 customers by revenue last quarter?" — Claude writes the SQL, runs it, returns the results.
Everything Claude needs to be your data science co-pilot.
Runs as a Model Context Protocol server. Claude Code discovers database tools automatically — no prompt engineering required.
PostgreSQL, Snowflake, BigQuery, Databricks, MySQL. Install only the drivers you need with optional extras.
Claude generates interactive Plotly visualizations from query results. Bar charts, scatter plots, time series — rendered inline.
Automatically inspects tables, columns, types, and foreign keys. Claude understands your data model before writing a single query.
All queries run as SELECT statements with row limits. Your production data stays safe — no accidental writes or deletes.
Browse Looker dashboards and explores directly from Claude. Pull existing SQL patterns into your analysis.
Install, configure, and start querying.
# 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]
{
"mcpServers": {
"dante": {
"command": "dante-ds",
"args": ["serve"],
"env": {
"DATABASE_URL": "postgresql://..."
}
}
}
}
Install only the drivers you need. Each database is an optional extra.
Stop context-switching between your editor and a SQL client. Let Claude handle the queries.
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.
From question to published report in minutes. No SQL required.
Point Dante at your Postgres warehouse, Databricks, Looker, or local Parquet files.
"Show me revenue by region for Q4" — the AI agent writes and executes the SQL for you.
One click turns your analysis into an interactive dashboard with charts, KPIs, and filters.
Get a clean URL like /app/q4-revenue and send it to your stakeholders.
A complete analytics platform — from raw SQL to polished, live dashboards.
Chat with an AI agent that writes SQL, runs Python, and builds visualizations. Powered by Claude with streaming responses.
Build dashboards from templates — KPI cards, chart grids, map explorers. AI generates the HTML, CSS, and JS.
Jupyter-style computational notebooks with a multi-step analysis pipeline. Code cells execute in isolated kernels.
Publish data apps with clean vanity URLs. Set visibility to public or org-only. Lock reports to prevent edits.
Build a library of notes, keywords, and SQL embeddings. The AI uses vector search to get smarter with every query.
Google OAuth, role-based access, encrypted credentials, per-user token budgets, and full usage tracking.
Bring your own data. Studio reads from your warehouse and BI tools — nothing to migrate.
Get from raw data to published report faster than your team can schedule a meeting about it.