ThoughtSpot Spotter MCP Server
Connect ThoughtSpot Spotter to your AI agents with the ThoughtSpot Spotter MCP server.
Updated
What is ThoughtSpot Spotter MCP?
The ThoughtSpot Spotter MCP server is a Model Context Protocol server that connects ThoughtSpot Spotter to AI agents and assistants as a set of tools. With it connected, an agent can work with ThoughtSpot Spotter (ai analytics agent — natural-language bi queries, liveboards, and data insights) 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 Spotter tools become available to the model.
Connect the ThoughtSpot Spotter MCP server
Connect ThoughtSpot Spotter MCP to Claude Code
- 1
Add the server
Use `claude mcp add` with the ThoughtSpot Spotter 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 Spotter tool to confirm the connection is live.
Connect ThoughtSpot Spotter MCP to Cursor
- 1
Open MCP settings
In Cursor, go to Settings → MCP → Add new server.
- 2
Add ThoughtSpot Spotter
Provide the ThoughtSpot Spotter MCP server URL or command and complete authentication.
- 3
Test
Reference ThoughtSpot Spotter from chat to confirm Cursor can reach the tools.
Sample use cases
An agent answers business questions by querying ThoughtSpot Spotter with natural language and returning formatted results
Self-service analytics for non-technical stakeholders without writing SQL.
A scheduled agent runs daily KPI queries through Spotter and posts results to a Slack channel
Automated daily metrics briefing without anyone logging into a dashboard.
An agent generates a weekly executive summary by pulling key metrics from ThoughtSpot Spotter and formatting a report
Consistent, automated executive reporting with live data.
An agent detects metric anomalies by comparing today's Spotter results against historical baselines
Early warning on KPI deviations before they appear in scheduled reports.
A support agent queries Spotter mid-conversation to pull account-level usage stats for a customer
Real-time data access during customer conversations without switching tools.
An agent builds a custom data extract from Spotter and pushes it to Google Sheets for a team's ad-hoc analysis
On-demand data exports to familiar formats without involving the data team.
An agent runs A/B test analysis queries through Spotter and summarizes results with statistical context
Faster experiment evaluation with data pulled and interpreted automatically.
Using ThoughtSpot Spotter MCP with Gamut
On Gamut, the ThoughtSpot Spotter MCP server becomes a tool your agents use inside an automated, event-driven workflow — triggered by an event or a schedule, acting through ThoughtSpot Spotter and your other connected MCP servers, with the connection managed by Gamut rather than a local config file.
Frequently asked questions
What is ThoughtSpot Spotter and how does the MCP server work?
ThoughtSpot Spotter is ThoughtSpot's AI-powered analytics interface that answers business questions in natural language. The MCP server lets agents query Spotter programmatically, enabling automated reporting and data retrieval workflows.
Do I need to write SQL to use the ThoughtSpot Spotter MCP server?
No. Spotter accepts natural language queries, so agents can ask business questions in plain English. ThoughtSpot translates the query to SQL internally and returns structured results.
Can the ThoughtSpot Spotter MCP server handle scheduled reports?
Yes. Agents in Gamut can run on a schedule, querying Spotter for the latest metrics and distributing results via Slack, email, or other channels at any cadence.
Is ThoughtSpot Spotter different from regular ThoughtSpot?
Spotter is ThoughtSpot's conversational AI layer built on top of the ThoughtSpot analytics platform. It adds natural language querying and AI-generated insights. The MCP server specifically connects to the Spotter interface.