Skip to main content
ThoughtSpot Spotter MCP logo
  • Category: model context protocol
  • Auth: DCR_OAUTH
  • Composio-managed OAuth available? No
  • Tools: 8
  • Triggers: 0
  • Slug: THOUGHTSPOT_SPOTTER_MCP
  • Version: 20261030_00

Tools

Slug: THOUGHTSPOT_SPOTTER_MCP_CHECK_CONNECTIVITYPing tool to test connectivity and authentication. You can use this if other tool calls are failing to verify if the connection is working.

Output

boolean
required
Whether the request was successful. If unsuccessful, you can ask the user to verify their MCP server configuration.
Slug: THOUGHTSPOT_SPOTTER_MCP_CREATE_ANALYSIS_SESSIONStart an analytical session with the Analytics Agent. This is the first step in a three-step workflow: create a session, send a message, then poll for updates. Once created, you can use the returned analytical_session_id to send analytical questions via send_session_message and retrieve answers via get_session_updates. Sessions are conversational, so you can ask follow-up questions in the same session without creating a new one. Using a single analytical session is preferable, because it reuses the same data source selection.

Input Parameters

string
The ID of the data source to query. You can provide this when the user has specified or confirmed a data source, or when context makes a particular source obvious. Omit it to let the Analytics Agent automatically select the most relevant source based on the question. A valid ID follows the following format: “xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx” (for example, “de1b3cfd-1725-400a-b6c7-0cd0f2b70bf1”). If you only have the data source name but not the ID, you can provide it in the additional_context field of the send_session_message tool instead.

Output

string
required
Identifier for the analytical session. You can use this to send messages or get updates on the session.
Slug: THOUGHTSPOT_SPOTTER_MCP_CREATE_DASHBOARDCreate a dashboard from a list of answers, allowing the user to revisit the results later. You can use this if the user asks for a dashboard or liveboard, or asks to save the results from the analysis. This can be a useful way to save the results to revisit later, or present them to other users.

Input Parameters

string
required
Title of the dashboard to be created.
array
required
List of answers to add to the dashboard. The order of tiles on the dashboard will match the order of answers in this list (top to bottom, left to right).
string
required
Intended to be a summary of the contents of the dashboard. You can fill this with information about the questions asked by the user and the analyses performed to answer those questions. You can include any action items or next steps the user should consider taking. The format for the note_tile field is raw unescaped HTML, and can include custom styles, text formatting, and colors. You can include emojis for visual appeal. At the end, you can add a line indicating the date the content was generated. The entire content of the note_tile should be in a single line with no line breaks. You can use
or CSS styling to add spacing inside the HTML content where needed, but avoid unnecessary whitespace inside the content. Use unescaped raw HTML such as <p> and not <p>. Example content: “<h2>Title of Note Tile</h2><p>Comprehensive summary of questions and answers used to generate the dashboard. Use HTML formatting:
- Text styling to highlight <strong>important phrases</strong>
- 🚀 Emojis for visual appeal

<em style=“color: #636e72;“>Generated on April 15, 2026</em></p>”.

Output

A URL link to the created dashboard. You can provide this link to the user to view the dashboard.
Slug: THOUGHTSPOT_SPOTTER_MCP_GET_SESSION_UPDATESGet the latest updates from the Analytics Agent. You can call this after send_session_message to retrieve the Agent’s response. If is_done is false, you can call this tool again to continue polling, as the Agent is still generating a response. Even if is_done is false, you can use the updates to show status updates or progress to the user, so that they are informed about the ongoing process. An empty session_updates list while is_done is false is normal; it means the Agent is still thinking. When is_done is true, the Agent has finished and the results in session_updates are complete, so you can present them to the user. You can also send a follow-up message in the same session after is_done is true. If the completed response indicates that no data or no results were found, AND the list_orgs tool is available to you, the requested data may live in a different org or the user may not have access to it in the current org: tell the user this and that they can call list_orgs to see their orgs (the active one is marked is_active) and switch_org to switch to another org, then retry. If list_orgs is not available, do not mention orgs.

Input Parameters

string
required
Identifier of the analytical session to get updates from.

Output

boolean
required
Whether the Analytics Agent has finished responding. If is_done is false, you can make another get_session_updates call to get the next set of updates.
array
required
List of incremental new updates from the analytical session. Updates returned in a previous response will not be sent again. This may be an empty list if the Analytics Agent is still thinking. You can instead use the is_done flag to know whether the Agent response is complete.
Slug: THOUGHTSPOT_SPOTTER_MCP_LIST_ORGSList the Orgs the authenticated user can access on the ThoughtSpot instance, including the ID, name, and description of each Org. The Org marked is_active: true is the one currently active for your account, which all tool calls operate against. Use this to tell the user which Org they are in. Only available when authenticated via OAuth. If the list is large , summarize or show only the most relevant orgs (e.g. the active one and a few others) rather than listing all of them, unless the user explicitly asks to see all orgs.

Output

array
required
The list of Orgs the user can access.
Slug: THOUGHTSPOT_SPOTTER_MCP_SEARCH_OBJECTSSearch for objects (Answers, Liveboards, Worksheets) in ThoughtSpot matching a given search term. Supports optional filters (types, owner, tag, modified_since, verified_only) and pagination (limit, cursor). Returns results (ranked), plus next_cursor. Each result carries: object_id, title, type (LIVEBOARD | ANSWER | LIVEBOARD_VIZ | WORKSHEET; LIVEBOARD_VIZ is a viz pinned on a Liveboard — render it as ‘Liveboard viz’), author_name, description, tags, last_modified (ISO-8601), verified, external_link, query (Answer/viz sage tokens; null for Liveboards) and confidence. Returns identifiers and metadata only — never the object’s data or contents, and it does not run queries.How to present the results: • Render as a table with fixed columns in this order: Object (the name, linked to external_link) · Type · Owner · Verified (✓ or —) · Last Modified. • Put the description and, for an Answer/viz, the query tokens as sub-lines under the name (e.g. ’↳ sales by region, last 3 months’) — never as their own columns. • Render last_modified as a plain date (2026-05-15), never the raw timestamp. • Lead with the top match; if the top 2–3 are close, present them as ranked candidates. • Never surface next_cursor or the numeric confidence in your prose.Outcomes other than a hit list: • status: "no_results" — the search ran but nothing matched. Tell the user nothing matched, and suggest broadening the term or dropping a filter. Do not invent results. • status: "error" — the search failed. Tell the user briefly using error.message; if error.retryable is true, offer to try again. Never show error.code.

Input Parameters

string
Restrict results to objects carrying this tag/sticker, matched by tag name (case-insensitive).
integer
The maximum number of results to return. Defaults to 10.
string
required
The search term to find objects for, matched against object names or descriptions.
array
Restrict results to these object types. Allowed values: ‘LIVEBOARD’, ‘LIVEBOARD_VIZ’ (a viz pinned on a Liveboard), ‘ANSWER’, ‘WORKSHEET’. Omit to search all types.
string
Opaque pagination cursor returned as next_cursor by a previous call. Omit for the first page.
string
Restrict results to objects authored by the provided user, matched against the author’s display name (case-insensitive).
boolean
If true, only return objects marked as verified.
integer
Only return objects last modified on or after this epoch-millisecond timestamp.

Output

object
Present only on error.
string ("no_results" | "error")
Absent on a successful hit list. ‘no_results’ = the query ran but matched nothing; ‘error’ = the search failed (see error).
array
required
Ranked results matching the search; empty for no_results/error.
string
Cursor to pass back as cursor for the next page; null when there are no more results, and omitted on error.
Slug: THOUGHTSPOT_SPOTTER_MCP_SEND_SESSION_MESSAGESend a message to a session with the Analytics Agent. The Agent may take some time to think and generate a response, so the response will not be returned immediately. Instead, you can use the get_session_updates tool to query for the latest updates on the session. After the Agent finishes responding (when get_session_updates returns is_done: true), you can send another message to the same session to ask follow-up questions without creating a new session. Do not send a new message until the Agent has finished responding to the previous message (when get_session_updates returns is_done: true). If the user wants to create a dashboard, do not send a message with that request; instead use the create_dashboard tool.

Input Parameters

string
required
A natural language analytical question or follow-up to send to the Analytics Agent.
string
Extra information which the Analytics Agent should be aware of while interpreting the message. You can use this field to provide background or external information relevant to the request, which the Agent would not be aware of. For example, “The user’s fiscal year starts in April”, or “The user is a manager of the West region”.
string
required
Identifier of the analytical session to send the message to.

Output

boolean
required
Whether the message was successfully sent. If unsuccessful, you can try sending the message again, or creating a new analytical session.
Slug: THOUGHTSPOT_SPOTTER_MCP_SWITCH_ORGSwitch the active Org. After switching, all subsequent tool calls (analysis sessions, answers, data sources, dashboards) operate against the selected Org. Pass an org_id returned by list_orgs. If you do not have access to the Org, the switch fails and the active Org is unchanged. The selection is durable and shared across all of your sessions — it persists across reconnects and applies to your other active conversations; it resets only on re-authentication or after prolonged inactivity. Only available when authenticated via OAuth.

Input Parameters

number
required
The id of the Org to switch to. Use an id returned by list_orgs. Subsequent tool calls in this session operate against this Org.

Output

boolean
required
Whether the Org switch was successful.
number
required
The id of the Org now active for the session.