---
canonical_url: "https://docs.composio.dev/toolkits/thoughtspot_spotter_mcp"
markdown_url: "https://docs.composio.dev/toolkits/thoughtspot_spotter_mcp.md"
product: "platform"
version: null
last_updated: null
---

# ThoughtSpot Spotter MCP

ThoughtSpot Spotter MCP brings governed enterprise analytics, natural-language questions, deep research, root-cause analysis, and insight generation to agents.

- **Category:** model context protocol
- **Auth:** DCR_OAUTH
- **Composio-managed OAuth available?** No
- **Tools:** 8
- **Triggers:** 0
- **Slug:** `THOUGHTSPOT_SPOTTER_MCP`
- **Version:** 20260929_00

## Tools

### Check connectivity

**Slug:** `THOUGHTSPOT_SPOTTER_MCP_CHECK_CONNECTIVITY`

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

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `success` | boolean | Yes | Whether the request was successful. If unsuccessful, you can ask the user to verify their MCP server configuration. |

### Create analysis session

**Slug:** `THOUGHTSPOT_SPOTTER_MCP_CREATE_ANALYSIS_SESSION`

Start 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data_source_id` | string | No | 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `analytical_session_id` | string | Yes | Identifier for the analytical session. You can use this to send messages or get updates on the session. |

### Create dashboard

**Slug:** `THOUGHTSPOT_SPOTTER_MCP_CREATE_DASHBOARD`

Create 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `title` | string | Yes | Title of the dashboard to be created. |
| `answers` | array | Yes | 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). |
| `note_tile` | string | Yes | 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 <br> 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 &lt;p&gt;. Example content: "<h2>Title of Note Tile</h2><p>Comprehensive summary of questions and answers used to generate the dashboard. Use HTML formatting:<br>- Text styling to highlight <strong>important phrases</strong><br>- 🚀 Emojis for visual appeal<br><br><em style="color: #636e72;">Generated on April 15, 2026</em></p>". |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `link` | string | Yes | A URL link to the created dashboard. You can provide this link to the user to view the dashboard. |

### Get session updates

**Slug:** `THOUGHTSPOT_SPOTTER_MCP_GET_SESSION_UPDATES`

Get 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `analytical_session_id` | string | Yes | Identifier of the analytical session to get updates from. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `is_done` | boolean | Yes | 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. |
| `session_updates` | array | Yes | 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. |

### List orgs

**Slug:** `THOUGHTSPOT_SPOTTER_MCP_LIST_ORGS`

List 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `orgs` | array | Yes | The list of Orgs the user can access. |

### Search objects

**Slug:** `THOUGHTSPOT_SPOTTER_MCP_SEARCH_OBJECTS`

Search 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `tag` | string | No | Restrict results to objects carrying this tag/sticker, matched by tag name (case-insensitive). |
| `limit` | integer | No | The maximum number of results to return. Defaults to 10. |
| `query` | string | Yes | The search term to find objects for, matched against object names or descriptions. |
| `types` | array | No | Restrict results to these object types. Allowed values: 'LIVEBOARD', 'LIVEBOARD_VIZ' (a viz pinned on a Liveboard), 'ANSWER', 'WORKSHEET'. Omit to search all types. |
| `cursor` | string | No | Opaque pagination cursor returned as `next_cursor` by a previous call. Omit for the first page. |
| `author_name` | string | No | Restrict results to objects authored by the provided user, matched against the author's display name (case-insensitive). |
| `verified_only` | boolean | No | If true, only return objects marked as verified. |
| `modified_since` | integer | No | Only return objects last modified on or after this epoch-millisecond timestamp. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `error` | object | No | Present only on error. |
| `status` | string ("no_results" | "error") | No | Absent on a successful hit list. 'no_results' = the query ran but matched nothing; 'error' = the search failed (see `error`). |
| `results` | array | Yes | Ranked results matching the search; empty for no_results/error. |
| `next_cursor` | string | No | Cursor to pass back as `cursor` for the next page; null when there are no more results, and omitted on error. |

### Send session message

**Slug:** `THOUGHTSPOT_SPOTTER_MCP_SEND_SESSION_MESSAGE`

Send 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `message` | string | Yes | A natural language analytical question or follow-up to send to the Analytics Agent. |
| `additional_context` | string | No | 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". |
| `analytical_session_id` | string | Yes | Identifier of the analytical session to send the message to. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `success` | boolean | Yes | Whether the message was successfully sent. If unsuccessful, you can try sending the message again, or creating a new analytical session. |

### Switch org

**Slug:** `THOUGHTSPOT_SPOTTER_MCP_SWITCH_ORG`

Switch 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `org_id` | number | Yes | 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

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `success` | boolean | Yes | Whether the Org switch was successful. |
| `active_org_id` | number | Yes | The id of the Org now active for the session. |