MCP App Store
by KeenEthics
Sisense icon

Sisense MCP Server for ChatGPT

By Sisense

Overview

Sisense connects ChatGPT to your Sisense tenant so you can browse connected data sources, run natural-language analytics queries, and build interactive charts and dashboards that you can save back to your own Sisense instance. Ask which data models you can use, what fields they hold, or a business question such as revenue by country. Sisense runs the query on its own engine, so answers come from your governed data. Charts and dashboards render in the conversation; a dashboard can be saved to your Sisense account with one click. You can also read your Pulse alerts and their evaluation results. For Sisense customers and their analysts. You sign in with your Sisense account, and the plugin sees only the data models and dashboards that account can access. It reads data; it does not change data models, rebuild them, or edit the underlying data.

How to connect

  1. ChatGPT: Open the Sisense listing in the ChatGPT app directory and choose Connect. ChatGPT listing Sisense exposes 30 tools here.

Tools

addDashboardFilters

ChatGPT
Adds filters to an existing dashboard from a natural-language description (filterDescription). Uses an LLM to turn the description into filters. It works on a draft held in this conversation; nothing is saved to Sisense.

addDashboardNarration

ChatGPT
Adds a Dashboard Narrative widget (an AI-written summary of the dashboard's data, generated when the user opens it) in a new top row. A dashboard holds at most one; remove it with removeDashboardWidgets and its widgetId (the one in layoutGrid). It works on a draft held in this conversation; nothing is saved to Sisense. This server registers exactly 30 tools: getDataSources, getDataSourceFields, getDataPreview, buildQuery, loadSkill, evaluatePulse, 9 chart tools, 9 dashboard tools and 6 Pulse read tools. There is no diagram or perspective tool here, and no interactive model browser. Table relationships are reported as text by getDataSourceFields. Capabilities outside these 30 tools are unsupported on this server.

addDashboardWidgets

ChatGPT
Adds widgets built earlier in this conversation to an existing dashboard. Optional placements position each widget (row, cell, before or after a widget already on the dashboard, or a height tier for a new row); omit them to append at the bottom. It works on a draft held in this conversation; nothing is saved to Sisense.

buildQuery

ChatGPT
Runs the analytics query described in queryPrompt and returns the results as structured data (tabular exploration, no chart). Filter values are taken literally. A filter on a text column — category, type, status, tier, band, segment — is built from the exact strings written in queryPrompt. Writing "except refunds" filters on the string "refunds" even when the column stores "Ret - Customer Refund", and the total comes back looking correct. Before a new query or a revision that filters such a column, read its values with getDataPreview and write those stored spellings into queryPrompt. The only user wording to pass through unchanged is an explicit text predicate — contains / starts with / ends with. A quoted value name is not one of these. New query — Only for the first query in a chain, or when the user clearly abandons the prior result and starts unrelated analysis. Omit priorQueryId (or null). Put the full natural-language intent in queryPrompt. Revise an existing query — Use for same-thread follow-ups that adjust the same analysis: different breakdown (e.g. by year, by category), added or removed filters, sort order, measure swaps, limits (Top N), trend/forecast, etc. Treat these as revisions, not separate unrelated queries. For revisions: - Set priorQueryId to the exact string in the queryId field from the latest successful tool result of this tool in the conversation (that value is the same id you pass as queryId when wiring a prior tabular result into the chart tool). - In queryPrompt, pass only the delta vs. that prior query — do not repeat the full prior specification. Return value includes queryId, queryState, and dataset rows. If the dataset includes a "sample" key, the full result was size-limited — call the chart tool with that queryId so the user can explore the complete result in the chart widget.

createDashboard

ChatGPT
Creates a new dashboard from widgets built earlier in this conversation, laid out in rows with a height tier each (small, medium or large). Pass the widgetIds from prior widget tool results; use rows: [] for an empty dashboard. Returns a dashboardId. It works on a draft held in this conversation; nothing is saved to Sisense.

createWidget

ChatGPT
Creates a new widget from a prior buildQuery result; today a widget is always a chart. Call buildQuery first and pass its queryId. Returns a widgetId, which the widget-editing tools and the dashboard tools take. It works on a draft held in this conversation; nothing is saved to Sisense.

evaluatePulse

ChatGPT
Runs a BRAND-NEW evaluation cycle for one existing agentic Pulse workflow right now: fetches it, runs its stored queries as the user (under their data security) and declared transforms, then decides whether to fire via the workflow's stored decisionSpec (json-rules-engine — chat-authored workflows are 'conditional'). Creates a Pulse notification with a narrative when the condition fires, sent to the recipients who share the user's data scope, plus the workflow's Slack, Zapier or webhook destinations when that scope includes the owner (stored as an event in the API; the narrative is written server-side when the workflow fires). Every query's fresh result is always recorded to history, whether or not the workflow fires — this is a WRITE, not a read. ROUTING — read this before calling: "did it fire", "check if it fired", "any events", "any notifications", "what happened last night", "why did it fire" are all INSPECT questions — call listPulseEvals or listPulseNotifications instead, never this tool. This tool cannot answer a question about a cycle that already ran; it can only start a new one. If a build or a scheduled cycle just happened, its evaluation has already run and is already recorded — inspect it, do not re-run it. Call this tool only when the user explicitly asks for a fresh check right now (e.g. "evaluate it now", "run the check again", "test the workflow") — never proactively after merely listing workflows, and never on a timer. Requires workflowId (the workflow's _id, e.g. from a prior listPulses lookup). Never modifies what the workflow monitors — queries/skill/decisionSpec/queryVersion stay untouched; redefining those is a separate, human-confirmed flow. This tool only records evaluation history and, when warranted, creates a notification — both automatic, no confirmation step, since neither changes what the workflow watches (API: event record) — but the new record it writes will appear in every eval-history listing of the users who share that data scope, alongside the cycles that ran on their own. This server registers exactly 30 tools: getDataSources, getDataSourceFields, getDataPreview, buildQuery, loadSkill, evaluatePulse, 9 chart tools, 9 dashboard tools and 6 Pulse read tools. There is no diagram or perspective tool here, and no interactive model browser. Table relationships are reported as text by getDataSourceFields. Capabilities outside these 30 tools are unsupported on this server.

getDataPreview

ChatGPT
Returns every distinct value stored in one text column, so a query filters on real values instead of guessed ones. Gives values plus complete. WHEN TO CALL — after getDataSourceFields (table and column names come from that listing; a guessed name fails the call) and BEFORE buildQuery, whenever the query will FILTER a text column that holds a fixed set of labels: category, type, status, tier, band, segment, region, and the like. The rule is about the column being filtered, not about how the user phrased the filter: - "high-income households", "premium tier", "still in process" — a concept that lives in a banded or coded column. The stored spelling (abbreviation, casing, boundaries) is the data's, not yours. Where the concept has no bucket of its own, name the bucket containing it. - "except refunds", "only wholesale accounts", "all but the unresolved" — the user NAMES members of the set. Their word is a description, not the stored value: an Account Type column may hold "WHSL - Wholesale Account" where the user said "wholesale", and a filter on the user's word matches nothing while the total looks correct. A value the user names is looked up by reading, never copied. Leaving a set out additionally needs complete: true. - "everything else", "unset", "blank" — claims about encoding. Naming no value is not safer; read the column and name the real values. The filter is built from whatever spellings appear in queryPrompt. Forwarding the user's wording into queryPrompt IS the guess this tool exists to prevent. Which columns hold labels is a judgement from the name — the listing gives names, not types or cardinality, so Brand, Country and City read both ways. Err toward reading: a needless read costs one call, a skipped one builds a filter that matches nothing and reports a total that looks right. DO NOT CALL only when: - The user gave an explicit TEXT-MATCHING PREDICATE — contains, starts with, or ends with ("name contains 'Logistics'", "numbers starting with 'INV'"). Pass it into queryPrompt unchanged. This is the only phrasing that counts as spelled out. Quotation marks are not a predicate: a quoted value name ("status is 'in progress'") is still a value, and still needs the read. - The column is an identifier, a name, free text, a date or a numeric measure — or no text column is filtered at all ("total revenue by region"). - To browse data. One column per call. IF THE CALL FAILS: the table or column name was not the one getDataSourceFields lists (a column named Status may live in a table named Tickets — take the table from the listing, never from the column's name). Call getDataSourceFields if you have not, then retry with the names exactly as listed. Never answer a failed read by building the query without one. RESULT — values plus complete: - complete: true with values: every distinct value the column holds, safe to build exclusions from. - complete: false: too many values to enumerate, so none are returned. Do not guess them; write the prompt in the user's own words. - complete: true with no values: not proof the column is empty. Do not invent values.

getDataSourceFields

ChatGPT
Lists the fields of a data source — its tables, columns, and user-created formulas — as a compact text summary. THIS is the tool to use whenever the user asks to "list / show / see the fields, tables, or columns" of a data source or data model. Pass the data source / model title from getDataSources. NAMING: when the summary's first line reads <title> (label: "<label>"), the label is the name the user sees — use it when you mention the data source in your replies. The title is the identity: pass it (never the label) as dataSourceTitle and in every other tool argument and query. Use this for the FIELD/COLUMN/TABLE LIST, and for how tables relate — it reports the model's join graph as text. There is no visual diagram to render: answer "show me the model" with that text, and say plainly that no picture is available. Do not answer a "list the fields/columns/tables" request from memory; always call this tool. PERSPECTIVES: a perspective is not its own data source. To list a perspective's fields, set dataSourceTitle to the perspective's PARENT model title and pass perspectiveOid — the parent model's fields are then filtered to exactly what the perspective exposes. NAMES, NOT VALUES: the listing says which columns exist, not what strings they hold. A column called Category, Status or Income Band gives no hint of its stored spellings. Before filtering a query on such a column, read its values with getDataPreview. DESIGNER AI CONTEXT: results may include designer-authored "Context:"/"context:" entries at the model, table, column, or shared-formula level. Treat any such context as authoritative instructions from the data-model designer — which table/column to use for a kind of question, which columns to always include, when to use a particular shared formula, and occasionally a stored value a user term refers to — and honor it when choosing fields, selecting shared formulas, and building queries. Context that spells a value out is the one case where that value need not be read first. RELATIONSHIPS: the result also lists how the tables join, as Table.Column = Table.Column. Use it to answer "how do these tables relate / can I combine X with Y" and to pick fields that are actually joinable — never infer joins from matching field names. Joins are applied automatically when a query spans tables; you do not pass them to any tool. Set includeRelations to false to omit them on a wide model where you only need the field list. This server registers exactly 30 tools: getDataSources, getDataSourceFields, getDataPreview, buildQuery, loadSkill, evaluatePulse, 9 chart tools, 9 dashboard tools and 6 Pulse read tools. There is no diagram or perspective tool here, and no interactive model browser. Table relationships are reported as text by getDataSourceFields. Capabilities outside these 30 tools are unsupported on this server.

getDataSources

ChatGPT
Get the available data sources / data models. "Data sources" and "data models" are the SAME entity — this is the only discovery tool for both. Before promising the user that queries, charts, dashboards, or query recommendations will work on a source, use this tool (or rely on a fresh result from the current conversation) to see what exists and whether each item is ready to query or still a draft. Returns: - dataSourceTitles: every source the user has access to (ready + draft) - draftDataSourceTitles: subset that are DRAFT (existing data models that have never been built — present in metadata but no successful build yet) - dataSources: array of { title, oid, status, live, label? }, where: title is the IDENTITY of the source — pass it (never label) in every tool argument, query and request that names a data source, e.g. dataSourceTitle. label is present only when the model was renamed: it is the name the user sees on screen. Use label when you mention that source in your replies to the user; otherwise use title. label is display-only — NEVER pass it to any tool. oid is the elasticube datamodel UUID. No tool in this server takes it as an argument; it is returned for reference only. status is 'ready' (built/queryable) or 'draft' (not built yet) * live is true for live/external connections (Snowflake, BigQuery, etc.) — these are NOT elasticubes ("cube" elsewhere means elasticube) and have no oid; they cannot be used with schema/perspective tools. Read this field directly from THIS result each time you need it — never assume or recall a source's live/cube status from an earlier turn. Workflow rules for drafts: - DRAFTS CANNOT BE QUERIED. Do NOT query, chart, or recommend queries on a draft, or build a dashboard from one — the query endpoints will reject it. - If the user asks to query/chart/analyze a draft, tell them it must be built first. This server cannot build it. When listing sources to the user, name each by its label when it has one, and mark drafts explicitly (e.g. "Sales DB (draft — not built yet)"). Data models an administrator has closed to AI are left out of this result. A model the user names that is not listed may exist but be unavailable to you: tell them you do not have access to it — never that it does not exist — and do not offer to rebuild or re-upload it. This server registers exactly 30 tools: getDataSources, getDataSourceFields, getDataPreview, buildQuery, loadSkill, evaluatePulse, 9 chart tools, 9 dashboard tools and 6 Pulse read tools. There is no diagram or perspective tool here, and no interactive model browser. Table relationships are reported as text by getDataSourceFields. Capabilities outside these 30 tools are unsupported on this server.

getPulse

ChatGPT
Reads one Pulse's full definition: queries, skill, decisionSpec, frequency, nextCheckTime (when it's next checked; absent when paused, cube-triggered or live alerting is off) with nextCheckText, evalMode, and its last-evaluated status (lastEvaluatedAt/lastEvalFired/lastEvalNarrative, set after every cycle in the user's data scope; lastEvalStatus 'error' means that check failed or didn't run, and it then has no narrative). State the next check from nextCheckText's weekday, date and time (translated when replying in another language), never by working out a weekday from nextCheckTime. Read-only.

getPulseEval

ChatGPT
Reads one evaluation cycle in full, by its evalId (e.g. from listPulseEvals or a notification's evalId). Works for any retained cycle, not only the recent window listPulseEvals returns (quiet cycles are kept 90 days, fired ones two years). If the answer already exists in a record ("did it fire", "why did it fire", "what happened last night"), read it here; evaluatePulse only runs a brand-new check, when the user explicitly asks for one. Read-only.

getPulseEvalResults

ChatGPT
Reads the raw per-query rows and transform outputs behind one cycle (the columns and rows each query returned, capped at 20 rows per query, with the true row count). Call it only as a drill-down after getPulseEval or listPulseEvals, when the narrative and signals are not enough and a claim needs checking against the real data. Returns an empty list in three cases: the cycle failed or was skipped (status 'error'), so it ran no queries; the cycle aged out (quiet cycles are kept 90 days, fired ones two years); or the cycle belongs to another data scope (e.g. a notification sent under the user's earlier data security). A notification's cycle always fired, so for one under two years old an empty list means another scope: say that cycle isn't in the user's history, not that it aged out. Never imply nothing happened. Read-only.

listPulseEvals

ChatGPT
Lists one Pulse's evaluation history (fired or not, errored or not), newest first, each with its narrative, trigger ('build'/'schedule'/'onDemand'/'create') and per-query signals. This is the audit trail. If the answer already exists in a record ("did it fire", "why did it fire", "what happened last night"), read it here; evaluatePulse only runs a brand-new check, when the user explicitly asks for one. Every check it returns belongs to the user's own data scope (the users who see the same rows under data security); users with different data security get their own checks and notifications from the same Pulse. Read-only.

listPulseNotifications

ChatGPT
Lists recent fired Pulse notifications. Omit workflowId for an overview across all agentic workflows in one call: each notification already includes its workflow name, so never call this once per workflow after listPulses. Pass workflowId only when the user named one Pulse. Every check it returns belongs to the user's own data scope (the users who see the same rows under data security); users with different data security get their own checks and notifications from the same Pulse. Read-only.

listPulses

ChatGPT
Lists the agentic Pulse workflows the user can see (their own and ones shared with them), one compact row each: enabled (false = paused), receiveNotifications (false = the user muted it), isOwner (only the owner can edit). Optional searchByName filters by name. Returns only enabled workflows unless includeDisabled is true; pass it when looking for a paused one (e.g. to resume it). Always quote counts from the result's counts field, never count rows yourself; when counts.hiddenDisabled > 0, say those paused workflows exist. Read-only; classic KPI, build and upgrade workflows are filtered out.

loadDashboard

ChatGPT
Loads an existing Fusion dashboard, by title or id, into the conversation as a draft that the other dashboard tools can edit. Nothing in Sisense changes. Returns a dashboardId. Titles are not unique: if more than one dashboard matches, the tool reports the candidates and the call must be repeated with dashboardId.

loadSkill

ChatGPT
Load detailed operational guidance for a workflow or a kind of question. Always call this before starting work, or answering a question, that a skill covers.

rebindWidgetQuery

ChatGPT
Points a chart built earlier in this conversation at new data. Call buildQuery first and pass its new queryId. Takes the widgetId from the latest successful widget tool result. It works on a draft held in this conversation; nothing is saved to Sisense.

removeDashboardWidgets

ChatGPT
Removes widgets from an existing dashboard by widgetId: the widgetId of each cell in the layoutGrid of the latest dashboard tool result. It works on a draft held in this conversation; nothing is saved to Sisense.

replaceDashboardWidgets

ChatGPT
Swaps a widget on a dashboard for a different widget, in the same row and cell. The widget to replace is its widgetId, as listed in the layoutGrid of the latest dashboard tool result; the new widget is a newWidgetId from a widget tool. Not for editing a widget in place: change the widget itself with the widget-editing tools, then pass its own id as both widgetId and newWidgetId to copy the edited widget into the dashboard. It works on a draft held in this conversation; nothing is saved to Sisense.

updateChartMeasureTypes

ChatGPT
Sets the chart type of individual measures in a combo chart (for example one measure drawn as a line over columns), from a natural-language description. Takes the widgetId from the latest successful widget tool result. It works on a draft held in this conversation; nothing is saved to Sisense.

updateChartTrendForecast

ChatGPT
Adds, changes or removes a measure's trend line or forecast on a chart, from a natural-language description. Takes the widgetId from the latest successful widget tool result. It works on a draft held in this conversation; nothing is saved to Sisense.

updateChartType

ChatGPT
Changes the chart type of a chart built earlier in this conversation (for example column to line), keeping its data. Takes the widgetId from the latest successful widget tool result. It works on a draft held in this conversation; nothing is saved to Sisense.

updateDashboardRowHeight

ChatGPT
Changes the height tier of an existing dashboard row. The row number comes from the layoutGrid of the latest dashboard tool result. It works on a draft held in this conversation; nothing is saved to Sisense.

updateDashboardTitle

ChatGPT
Renames an existing dashboard. It works on a draft held in this conversation; nothing is saved to Sisense.

updateWidgetDataOptions

ChatGPT
Edits a chart's data options, including ALL colors (line, bar, series and slice colors, seriesToColorMap, measure color), showing a measure on the right axis, and related mapping, from a natural-language description. Use this rather than updateWidgetStyle whenever a color changes. Takes the widgetId from the latest successful widget tool result. It works on a draft held in this conversation; nothing is saved to Sisense.

updateWidgetSorting

ChatGPT
Changes how a chart's data is sorted, from a natural-language description. Takes the widgetId from the latest successful widget tool result. It works on a draft held in this conversation; nothing is saved to Sisense.

updateWidgetStyle

ChatGPT
Changes a chart's legend, labels and axis chrome (for example moving the legend, an axis title, or enabling the secondary axis), from a natural-language description. Not for colors: series, bar, line and slice colors use updateWidgetDataOptions. Takes the widgetId from the latest successful widget tool result. It works on a draft held in this conversation; nothing is saved to Sisense.

updateWidgetTitle

ChatGPT
Renames a chart built earlier in this conversation. Takes the widgetId from the latest successful widget tool result. It works on a draft held in this conversation; nothing is saved to Sisense.

Capabilities

InteractiveWrites

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/sisense"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/sisense)