{
"mcpServers": {
"ThoughtSpot": {
"command": "npx",
"args": [
"mcp-remote",
"https://agent.thoughtspot.app/mcp?api-version={YYYY-MM-DD}" // replace YYYY-MM-DD with an actual date string
]
}
}
}Connecting MCP Server to MCP clients
Table of Contents
If your application already has an AI-native experience or supports MCP-aware agents and LLMs, you can integrate ThoughtSpot analytics directly into your app’s agentic experience by connecting the MCP Server to your client.
In this plug-and-play integration, your application’s chat interface and LLM orchestrate conversation sessions. The MCP Server exposes ThoughtSpot’s analytics capabilities as tools, which your agent or LLM can invoke as needed. This approach allows you to bring ThoughtSpot analytics into your own AI-native experience and use it as a data and analytics provider through the MCP Server, while your system controls user interaction and orchestration logic.
When your MCP client is connected to the ThoughtSpot MCP Server, the AI agent/LLM can:
-
Automatically discover ThoughtSpot MCP tools.
-
Call the MCP tools to determine the data context and answer data questions.
-
Create a Liveboard with the visualizations generated during the interaction.
Before you begin🔗
Before you begin, review the following prerequisites:
-
Ensure that your setup has access to a ThoughtSpot application instance with 10.11.0.cl or a later release. For MCP Server with Spotter 3 capabilities, ensure that your ThoughtSpot instance is 26.2.0.cl or later.
-
Ensure that the users have the necessary permissions to view data from relevant models and tables in ThoughtSpot. Existing RLS/CLS rules on tables are enforced automatically in data source responses. To create charts or Liveboards from a conversation session, data download and content creation privileges are required.
Connecting clients that support remote MCP servers🔗
To connect a client that supports remote MCP servers natively, add the MCP Server endpoint to your client’s configuration settings.
For OAuth clients, the following options are available:
-
https://agent.thoughtspot.app/mcp?api-version=latest
This URL always points to the latest version. -
https://agent.thoughtspot.app/mcpNoteCurrently, this URL points to the baseline version with legacy MCP tools. It will resolve to the latest version in the near future. During this period, you can switch to
https://agent.thoughtspot.app/mcp?api-version=latestto access the latest MCP tools. -
https://agent.thoughtspot.app/mcp?api-version={YYYY-MM-DD}
If you want to pin a specific version, use this URL format.
|
Important
|
The |
For more information about how to register a remote MCP Server, see your client’s documentation.
Connecting MCP Server to local MCP clients🔗
For MCP clients that do not natively support configuring a remote MCP Server URL, you must use the mcp-remote component. For desktop clients that rely on local MCP components, ensure that Node.js version 22 or later is installed on your system.
Authenticating users🔗
In a plug-and-play integration, the most common way to authenticate users is through OAuth tokens. This method allows you to leverage your existing IdP or SSO configuration for ThoughtSpot login and rely on the platform to initiate a browser-based sign-in flow.
OAuth flow🔗
In a typical OAuth flow:
-
The ThoughtSpot MCP Server is configured as a connector/tool in the MCP client.
-
When the user connects, the client redirects the user to ThoughtSpot to sign in.
-
After successful login, the client stores the issued OAuth tokens and includes them with each MCP tool call to the ThoughtSpot MCP Server, which then calls ThoughtSpot on behalf of that user.
OAuth client registration🔗
OAuth clients can be registered in one of the following ways:
-
For MCP hosts that support Dynamic Client Registration (DCR), the OAuth client is registered automatically.
-
For MCP hosts that do not support dynamic registration or that require static client credentials, you must manually register an OAuth client, obtain the OAuth client ID and OAuth client secret, and then configure these in the MCP host when adding ThoughtSpot as an MCP connector. The generated client details are only shown once and cannot be retrieved later.
To register a client, visit ThoughtSpot MCP OAuth Client Registration. When registering the OAuth client, add your ThoughtSpot instance URL to the appropriate field. This ensures that users are not prompted to enter the instance URL during the OAuth flow, and the OAuth redirect returns correctly to your ThoughtSpot environment after login.
Verifying integration🔗
After the MCP Server is connected, some clients show ThoughtSpot Data Sources under a Resources or Datasets section.
To verify the integration:
-
Start a chat session with the agent and verify the response.
-
Verify that MCP tools are being called to generate responses. See the MCP tool reference guide for information about tool calls.
-
Try the Liveboard creation request and verify whether a Liveboard is added to your ThoughtSpot application.
Troubleshooting errors🔗
- MCP Server is not connected
-
-
Verify that the MCP Server is reachable.
-
Ensure that you have access to a ThoughtSpot instance.
-
Ensure that there are no configuration errors.
-
If the issue persists, verify the logs and contact ThoughtSpot Support for assistance.
-
- Authentication failure
-
If user authentication fails, or if the server returns HTTP 500, 401, or 403 status codes:
-
Verify whether the MCP Server endpoint and ThoughtSpot host are correctly configured in your client and are reachable.
-
Check whether the user session has expired. Log in to your ThoughtSpot application to start a new session.
-
Verify whether the user has the necessary privileges to view data or create content.
-
Additional resources🔗
-
For information about the MCP Server features and architecture, see MCP Server integration.
-
To view the MCP Server code, go to the MCP Server GitHub repository.