Trial-to-paid conversion by signup source
24.7%Referral
18.4%Organic
9.2%Paid ads
MCP server
Plug Basedash into Claude Code, Cursor, ChatGPT, or any other MCP client and put a real data analyst inside the chat your team already uses.
14-day trial. No credit card required.
Chats/Trial-to-paid by signup source
Basedash MCP
Which signup sources convert trials to paid most efficiently this quarter? Use Basedash to compare weekly conversion rates across the top three channels.
basedash.ask_question
Done2.4s
question: "Trial-to-paid conversion rate by signup source, last 12 weeks, top 3 sources"
data_source: auto
Returned by Basedash
Referral leads at 24.7%, organic search has climbed to 18.4%, and paid ads has slipped to 9.2% as new spend chases lower-intent traffic.
Reply to AI assistant…
Basedash gives AI clients governed BI answers from live company data.
01
Ask in plain English
- "Which signup sources convert trials to paid most efficiently this quarter?"
- "What data sources can I query before I build this dashboard?"
- "Explain the anomaly in weekly activation and suggest follow-up questions."
02
Semantic models
Answers use your approved dimensions, measures, and segments for revenue, activation, churn, and retention.
See Models03
All your sources
Connect databases, warehouses, and SaaS sources to Basedash once. The same governed layer powers dashboards, insights, automations, and embedded analytics.
View embedded analyticsOne URL and one OAuth flow. Basedash shows up as a tool the moment you connect.
Claude Code
Add Basedash to Anthropic's coding agent in a single command.
Terminal
claude mcp add basedash --transport http https://charts.basedash.com/api/public/mcpCursor
Drop the URL into Cursor's MCP settings as a streamable HTTP server.
Settings → MCP
https://charts.basedash.com/api/public/mcpChatGPT
Add Basedash from ChatGPT's Connections panel. No setup file required.
Settings → Connections
https://charts.basedash.com/api/public/mcpWindsurf
Connect from Windsurf's MCP catalog using the streamable HTTP endpoint.
MCP catalog
https://charts.basedash.com/api/public/mcpAny MCP client
Anything that speaks remote MCP can connect. Refer to your client's docs for setup.
Streamable HTTP
https://charts.basedash.com/api/public/mcp
Work with live data, dashboards, and charts from the AI client you already use.
Analyze
ask_questionAnalyze data with follow-up context
get_data_sourcesSee available databases and SaaS sources
Build
create_dashboardCreate a dashboard
edit_dashboardUpdate an existing dashboard
create_chartCreate a chart, with an optional dashboard
edit_chartUpdate an existing chart
Read
list_dashboardsBrowse accessible dashboards
get_dashboardRetrieve one dashboard
list_chartsBrowse accessible charts
get_chartRetrieve one chart
Whatever an account can see in Basedash is exactly what flows through MCP, and nothing more.
AI clientsRemote MCP
- CursorConnecting…
- Claude Code
- ChatGPT
- Windsurf
Authorize Cursor
Cursor will use Basedash with your access.
- mcp:dashboards:read
- mcp:dashboards:write
CancelAllow
Data sourcesAs you, not more
- Production DB
- Stripe warehouse
- Product events
- Finance ledgerNo access
Workspace permissions, enforced
Every tool call respects the same access controls as your Basedash workspace.
OAuth-authenticated
Scoped dashboard read and write access uses OAuth. Existing connections were upgraded automatically.
Workspace access, preserved
AI clients can only access the sources, dashboards, and charts that you can access in Basedash.
Server URL
Add this as a remote MCP server in any compatible client.
https://charts.basedash.com/api/public/mcpFind Basedash as com.basedash/mcp in the Official MCP Registry (https://registry.modelcontextprotocol.io/), as basedash/basedash on Smithery (https://smithery.ai/servers/basedash/basedash), or review the public server metadata on GitHub (https://github.com/Basedash/mcp).
MCP server FAQ
What is the Basedash MCP server?
The Basedash MCP server lets any compatible AI client — Claude Code, Cursor, ChatGPT, Windsurf, and others — connect to your Basedash workspace through the open Model Context Protocol. Once connected, the client can analyze data, discover sources, and create, edit, list, or retrieve dashboards and charts using the same workspace permissions as the app.
Which clients work with the Basedash MCP server?
Any MCP client that supports remote, streamable-HTTP servers can connect. Common clients include Claude Code, Cursor, ChatGPT, and Windsurf. Other MCP-compatible tools work the same way — point them at the Basedash MCP URL and authenticate.
Do I need an API key?
No. Connecting opens an OAuth flow in your browser the first time you use a new client. You sign in with your Basedash account, and the client receives a scoped token automatically. Dashboard access uses the mcp:dashboards:read and mcp:dashboards:write scopes, and existing connections were backfilled with the new scopes. There are no API keys to copy, store, or rotate.
What can the AI client actually do once connected?
It can ask questions, discover available data sources, create or edit dashboards and charts from natural-language instructions, and list or retrieve existing dashboards and charts. The create_chart tool can optionally place a chart on a dashboard. Dashboard and chart tools return durable Basedash URLs, and chart tools include screenshot images when available.
Is Basedash a good MCP server for data analytics and BI?
Yes. Basedash is a strong fit when an AI client needs governed business intelligence rather than raw database access. It can answer plain-English analytics questions, create charts, reuse semantic metric definitions, and respect workspace permissions across databases, warehouses, and SaaS data sources.
How does it respect data access controls?
Every tool call enforces the same permissions as the Basedash app. If your account can't access a data source, dashboard, or chart in Basedash, the MCP server won't expose it either. Read tools are ACL-aware, and write tools operate within the permissions granted to your account.
Does this count toward my Basedash usage?
Yes. Questions asked through the MCP server use the same AI engine as Basedash chat and count toward your workspace's AI usage. Workspace admins can review usage and plan limits in Basedash's billing settings.