Treasure Data MCP Server
treasure-dataLABSCO SUMMARY
Analytics answers that come out of your governed model, so the numbers match what the rest of the business sees.
The value over pointing a model at the warehouse is the semantic layer: definitions, row-level and object-level security already live in ThoughtSpot, and the answers arrive through them. It also writes back — Liveboards and embeddable visualizations get created from the same conversation that produced the question.
What it is
ThoughtSpot's Spotter server, hosted by ThoughtSpot: it authenticates against your instance and answers from your own data through the semantic model already defined there.
What you get
- Natural-language questions answered from live data in your ThoughtSpot instance, not from a copy
- Liveboards and visualizations created programmatically out of the conversation
- Embeddable visualizations generated for use elsewhere
- Search across existing ThoughtSpot content by name, author, tag or type
- Answers that respect the governed semantic layer, including row-level and object-level security, so no analytics logic has to be rebuilt on your side
- Date-based API versioning: pin the tool contract by appending an api-version to the endpoint, or leave it off to track the latest
Requirements
A ThoughtSpot instance and an account on it. The hosted endpoint is https://agent.thoughtspot.app/mcp over streamable-http, with SSE alongside it. Clients that cannot do dynamic client registration register manually at https://agent.thoughtspot.app/clients — the OAuth client ID and secret are shown once and never again — and that registration can pin a ThoughtSpot URL so users are not asked for it. There is also a bearer-token endpoint that takes an Authorization header, with the instance either folded into it as token@ts-host or sent separately as X-TS-Host. Published on npm as @thoughtspot/mcp-server for running it yourself.
Setup effort
Paste a URL — add the servers you want to your client
USE CASES
01
Answering a business question without building a report
Ask in plain language and get an answer computed from live data through the governed model.
02
Turning a good answer into something the team keeps
Create the Liveboard and its visualizations directly, instead of rebuilding the question in the UI.
03
Finding what analysis already exists
Search existing content by name, author, tag or type before someone builds it a second time.
04
Putting a chart into your own product
Generate an embeddable visualization from the answer and drop it into the surface your users already use.
05
Keeping an integration stable across releases
Pin the endpoint to a dated api-version so tool changes land when you choose them.
BEFORE YOU INSTALL
What to know first
Requires
A ThoughtSpot account on your ThoughtSpot instance, signed in over OAuth when your client connects; The Spotter MCP Server add-on, available with the ThoughtSpot Enterprise Edition and ThoughtSpot Embedded licence plans; For clients without dynamic client registration: an OAuth Client ID and Client Secret, registered at https://agent.thoughtspot.app/clients
Where it runs
All 4 documented clients connect to a hosted endpoint.
INSTALLATION
Connect your client
The vendor hosts 2 servers, each with its own URL.
Server setup
ENDPOINT URLS
https://agent.thoughtspot.app/mcp?api-version=latest
https://agent.thoughtspot.app/token/mcpMCP Clients
Claude — OAuth, ChatGPT — OAuth, Gemini — OAuth
URL
https://agent.thoughtspot.app/mcp?api-version=latestAny MCP client — bearer token
ANY MCP CLIENT — BEARER TOKEN · URL
https://agent.thoughtspot.app/token/mcp
