Connect the way you already work.
An MCP server for AI agents, native Python and .NET clients, a JDBC driver and a REST API — the same catalogs, the same access rules and the same cost checks, whichever way the query comes in.
- Identity
- Role access
- Cost check
MCP server
Give your AI assistant a safe way in.
A remote Model Context Protocol server lets Claude, Cursor and your own agents browse catalogs, describe tables and run SQL. Calls sign in with OAuth, stay scoped to your workspace, and are read-only unless you grant more — and every query clears a cost gate before it executes, so an agent can explore without running up the bill.
{
"mcpServers": {
"thunderduck": {
"url": "https://mcp.thunderduck.ai/mcp"
}
}
}The tools your team already opens every day.
Agents over MCP, notebooks and dataframes over Python, BI and IDEs over JDBC and SQLAlchemy, services over .NET and REST. One API token per person or service, and every query shows up in the same history.
Claude · ChatGPT · Cursor
Jupyter & Colab
pandas
Apache Superset
DataGrip
Dapper (.NET)
Any JDBC tool
- curl & scripts
More clients and orchestrators on the way.
Native Node.js and Go clients, operators for Airflow, Prefect and Dagster, and a path for Tableau, Power BI, Excel and Google Sheets. Need one of these first? Tell us.
Node.js clientSoon
Go clientSoon
Airflow operatorSoon
Prefect tasksSoon
- Dagster resourceSoon
Google SheetsSoon
- Tableau · Power BISoon
- ODBC driverSoon