ThoughtSpot

listing.by

Ask questions of your ThoughtSpot data, get live answers and create Liveboards from your AI assistant.

state.auth.long (state.auth.title)Streamable HTTP

listing.connect

listing.explain.oauth

https://agent.thoughtspot.app/mcp

listing.note.oauth

listing.share.h

listing.share.p

mcp.tc/i/thoughtspot

listing.about

ThoughtSpot Spotter MCP Server connects an assistant to your ThoughtSpot instance. It provides tools for querying and retrieving relevant data, returns live answers from your own data, and can create Liveboards.

It runs as a hosted streamable HTTP endpoint with OAuth sign-in, where you enter your ThoughtSpot instance URL during authorization. A bearer-token variant is available using Authorization and X-TS-Host headers. It needs a ThoughtSpot instance with the MCP add-on (Enterprise Edition or Embedded). Add ?api-version=latest or ?api-version=YYYY-MM-DD to choose a tool version.

listing.can

  • Ask natural-language questions of ThoughtSpot data
  • Retrieve live answers from your own instance
  • Create Liveboards
  • Pick a tool version with the api-version query parameter
  • Sign in with OAuth or use a bearer token

listing.tools

listing.notools.oauth

listing.prompts

  • Ask ThoughtSpot what our total sales were by region last quarter.

  • Create a Liveboard with the answers about monthly revenue.

  • Which products had the highest return rate this year?

listing.setup.h

listing.setup.oauth

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport http thoughtspot https://agent.thoughtspot.app/mcp
  1. Start Claude Code, type /mcp, pick thoughtspot and choose Authenticate. A browser window opens for the ThoughtSpot sign-in.

Add --scope user to make it available in every project, not just this one.

Claude Desktop

  1. Open Settings → Connectors and click Add custom connector.
  2. Name it ThoughtSpot and paste this URL:
https://agent.thoughtspot.app/mcp
  1. Click Add, then Connect, and sign in when ThoughtSpot asks.

Claude Desktop's JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

claude.ai

  1. Open the connector form on claude.ai. This button fills in the name and URL for you:
  1. Check that the URL reads https://agent.thoughtspot.app/mcp and click Add.
  2. Click Connect and sign in when ThoughtSpot asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.

ChatGPT

  1. On chatgpt.com, open Settings → Security and login and turn on Developer mode.
  2. Go to chatgpt.com/plugins and click + to create an app for a remote MCP server.
  3. Paste https://agent.thoughtspot.app/mcp as the server URL and choose OAuth. ChatGPT sends you to ThoughtSpot to sign in.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "thoughtspot": {
      "url": "https://agent.thoughtspot.app/mcp"
    }
  }
}

Cursor shows Needs login next to the server. Click it to sign in.

VS Code

Or from a terminal:

code --add-mcp '{"name":"thoughtspot","type":"http","url":"https://agent.thoughtspot.app/mcp"}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "thoughtspot": {
      "type": "http",
      "url": "https://agent.thoughtspot.app/mcp"
    }
  }
}

VS Code asks you to sign in the first time the server starts.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "thoughtspot": {
      "serverUrl": "https://agent.thoughtspot.app/mcp"
    }
  }
}
  1. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.

Codex

codex mcp add thoughtspot --url https://agent.thoughtspot.app/mcp
codex mcp login thoughtspot

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.thoughtspot]
url = "https://agent.thoughtspot.app/mcp"

Gemini CLI

gemini mcp add --transport http thoughtspot https://agent.thoughtspot.app/mcp

Then, inside Gemini CLI, run /mcp auth thoughtspot to sign in.

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI's settings file.

{
  "mcpServers": {
    "thoughtspot": {
      "type": "http",
      "url": "https://agent.thoughtspot.app/mcp"
    }
  }
}

Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.

Client only starts local servers? Bridge it with npx -y mcp-remote https://agent.thoughtspot.app/mcp.

listing.faq

Can I paste mcp.tc/i/thoughtspot into my MCP client?

No. mcp.tc links are pages, not server addresses. Connect with https://agent.thoughtspot.app/mcp, so your client talks to ThoughtSpot directly. The sign-in token only works there anyway. The quick link is for sharing: it opens this page, with setup steps for every client.

Does ThoughtSpot need an API key or a sign-in?

Yes, you need a ThoughtSpot account. The first time your client connects, it opens ThoughtSpot's sign-in page. The token goes straight to the server's own URL, never through mcp.tc.

Is ThoughtSpot a remote or a local server?

Remote. ThoughtSpot hosts it at https://agent.thoughtspot.app/mcp, and it speaks Streamable HTTP. There's nothing to install.

What can ThoughtSpot do?

You can ask natural-language questions of ThoughtSpot data, retrieve live answers from your own instance and create Liveboards.

Which clients can use it?

Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT in developer mode, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.

Who wrote this page?

mcp.tc's robot read ThoughtSpot's own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can't confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

listing.em.h

listing.em.lead listing.em.how

listing.em.badge

em.prev_lightem.prev_dark
Markdown
[![ThoughtSpot on mcp.tc](https://mcp.tc/i/thoughtspot/badge.svg)](https://mcp.tc/i/thoughtspot)
HTML
<a href="https://mcp.tc/i/thoughtspot"><img src="https://mcp.tc/i/thoughtspot/badge.svg" alt="ThoughtSpot on mcp.tc" height="20"></a>

listing.em.badge_note

listing.em.widget

HTML
<script src="https://mcp.tc/w/thoughtspot.js" async></script>

listing.em.widget_note

iframe

HTML
<iframe src="https://mcp.tc/embed/thoughtspot" title="ThoughtSpot on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

listing.em.iframe_note

JSON

listing.em.json

https://mcp.tc/i/thoughtspot.json

listing.em.fields

listing.disclaimer_checked