ThoughtSpot MCP Server
Connect ThoughtSpot to your AI agents with the ThoughtSpot MCP server.
Updated
What is ThoughtSpot MCP?
The ThoughtSpot MCP server is a Model Context Protocol server that connects ThoughtSpot to AI agents and assistants as a set of tools. With it connected, an agent can work with ThoughtSpot (data analytics and business intelligence) directly — instead of you copying data in and out by hand.
It is a remote MCP server that uses OAuth, so you point your client at the server URL, authorize once, and the ThoughtSpot tools become available to the model.
Connect the ThoughtSpot MCP server
Connect ThoughtSpot MCP to Claude Code
- 1
Add the server
Use `claude mcp add` with the ThoughtSpot MCP server URL (or its `npx` command), following the official docs.
- 2
Authorize
Complete authentication (OAuth) so Claude Code can call the server.
- 3
Verify
Ask Claude to use a ThoughtSpot tool to confirm the connection is live.
Connect ThoughtSpot MCP to Cursor
- 1
Open MCP settings
In Cursor, go to Settings → MCP → Add new server.
- 2
Add ThoughtSpot
Provide the ThoughtSpot MCP server URL or command and complete authentication.
- 3
Test
Reference ThoughtSpot from chat to confirm Cursor can reach the tools.
Sample use cases
An agent queries ThoughtSpot for sales performance data and generates a formatted weekly report
Automated sales reporting with live warehouse data, no manual exports.
A scheduled agent monitors ThoughtSpot dashboards for metric thresholds and sends alerts when breached
Proactive alerting on business KPIs without building custom monitoring.
An agent answers ad-hoc data questions from stakeholders by searching ThoughtSpot and summarizing results
Self-service analytics through conversation instead of dashboard navigation.
An agent pulls cohort retention data from ThoughtSpot and compiles it into a product review deck
Faster product review preparation with automated data gathering.
An agent syncs ThoughtSpot query results to a Google Sheet that feeds a team OKR tracker
Live OKR tracking without manual data updates each week.
An agent runs competitor pricing analysis queries in ThoughtSpot and flags changes above a threshold
Automated competitive intelligence with alerts on meaningful price movements.
An agent creates ThoughtSpot saved searches for new team members based on their role and department
Faster onboarding to analytics with pre-configured, role-relevant views.
Using ThoughtSpot MCP with Gamut
On Gamut, the ThoughtSpot MCP server becomes a tool your agents use inside an automated, event-driven workflow — triggered by an event or a schedule, acting through ThoughtSpot and your other connected MCP servers, with the connection managed by Gamut rather than a local config file.
Frequently asked questions
What analytics capabilities does the ThoughtSpot MCP server provide?
The server gives agents access to ThoughtSpot's search-driven analytics platform. Agents can run queries, access saved answers and liveboards, retrieve data results, and interact with ThoughtSpot's AI-powered search.
Can the ThoughtSpot MCP server connect to my data warehouse?
ThoughtSpot connects to your data warehouse (Snowflake, BigQuery, Redshift, Databricks, etc.) directly. The MCP server queries ThoughtSpot, which in turn queries your warehouse, so agents get live data without direct warehouse access.
Does the ThoughtSpot MCP server support natural language queries?
Yes. ThoughtSpot's core interface is search-based, so agents can pass natural language or keyword queries. ThoughtSpot interprets the search and returns structured data results.
Can I use both ThoughtSpot and ThoughtSpot Spotter MCP servers?
Yes. They serve complementary purposes: the ThoughtSpot server accesses the full analytics platform (liveboards, saved answers), while Spotter provides a conversational AI interface. Use whichever fits your workflow.