ask_question
Ask a plain-English data question; Basedash's AI data analyst generates validated SQL, returns numbers, charts, and reasoning; continues the same chat across follow-ups
LABSCO SUMMARY
Per-call permission enforcement is what makes a two-tool answer engine safe to point at a warehouse.
The risk with natural-language SQL is not a bad query — it is a query against data the asker should not see. Checking workspace permissions on every call, rather than trusting the token issued at connect time, closes that. The narrow surface is a feature too: nothing here can write, and get_data_sources tells the agent what is reachable before it starts guessing table names.
What it is
Basedash's public endpoint. The surface is deliberately tiny — one tool to see what data exists, one to ask about it — with their AI analyst generating and validating the SQL behind the scenes.
What you get
- ask_question — a plain-English data question, answered with numbers, charts and the reasoning behind the query
- get_data_sources — every connected database, warehouse and SaaS source the user is allowed to see
Requirements
Browser OAuth on first connection, with a scoped token per client and no API keys anywhere. Workspace permissions are enforced on every call rather than at connection time.
Setup effort
Paste a URL, then authorize — add the endpoint to your client, then approve the OAuth consent screen
USE CASES
01
Answering a number question directly
Ask in business terms and get the figure plus the SQL that produced it, so the answer is checkable.
02
Seeing what data the agent can reach
List the connected sources the current user is permitted to see before asking anything.
03
Letting a non-analyst self-serve
Permissions are enforced per call, so opening this up does not open up the warehouse.
2 tools
Listed in project docs. Your client may show a different list.
get_data_sources
List every connected database, warehouse, and SaaS source in the workspace the user is allowed to access (Postgres/MySQL, BigQuery/Snowflake, 750+ SaaS via Fivetran or MCP connectors)
BEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
- an MCP client that can reach a remote endpoint
- Browser-based OAuth on first connection; scoped token per client; workspace permissions enforced per call; no API keys
INSTALLATION
Connect your client
Add the endpoint to your client, then approve the OAuth consent screen.
Server setup
ENDPOINT URL
https://charts.basedash.com/api/public/mcpRequirements
- Browser-based OAuth on first connection; scoped token per client; workspace permissions enforced per call; no API keys
