We first launched @Basedash earlier this year as an AI-native chart builder. You just describe the chart you want, and Basedash uses AI to visualize your data, no SQL required.
Now we're gearing up for our biggest update yet, launching here on Product Hunt tomorrow. Without spoiling anything, it should enable many more business users to finally get the data answers they need, without bugging engineers or data analysts on their team.
Basedash
@maxmusing flipping the integration direction is the right call. Every other BI tool asks agents to come to the data — this makes the data go to where the agent already is. The permissions-inheritance model is the part I'd bet on: agents querying live numbers inside the same access controls your team trusts removes the "shadow analytics" problem. How are you handling schema discovery for databases with hundreds of tables — does the MCP expose a search/filter layer or does the agent get the full schema dump?
Flipping the model so Basedash plugs into your AI tools instead of the other way around is great because that's where the queries actually happen. I'm curious to know if the MCP server handle ambiguous questions where the answer depends on how a metric is defined, or if it surface the raw data and let the LLM interpret.
very fascinated by the fact that we can now integrate a BI model into any mcp- compatible tool. I am very interested to know more about the administrative side of things or more like if a company could control what rows/columns a user can access as there can be many attributes containing sensitive info that the company would not like for the users to see.
Hookdeck
Love @Basedash. The MCP could be a game changer for some of my Claude cowork workflows 🙌