MCP Tools and Usage

Last updated: November 8, 2026

Tier Deployment
Launch     Grow    Enterprise Cloud     On-Prem

This page covers the tools the server exposes and how to use them. To connect a client first, see Connecting an AI Agent.

Available Tools

The server exposes the following tools. They read data and metadata, build charts and dashboards inside the conversation, and can run an existing Pulse on demand. They never create or modify your models, dashboards, Pulses, or data. Dashboards built in a conversation are drafts and are not saved to Sisense. Every tool runs with the signed-in user's own permissions, so an agent sees only the data and Pulses that user can already access.

Discover

Tool What It Does

getDataSources

Lists the data models and data sources you can access, with their build status. This is how the agent finds what is available to query.

getDataSourceFields

Returns the tables, columns, relationships, and formulas of a chosen data source: the schema and semantic definitions the agent reads before it queries. Can be scoped to a specific perspective.

Query

Tool What It Does

buildQuery

Runs a natural-language query against a chosen data model and returns the result set. The query is resolved against your semantic model, so it uses your governed metrics and relationships. Results are cached in the session so later steps can build on them. When a result is too large to return in full, only a representative sample is shown, and the agent is prompted to build a chart with createWidget so you can explore the complete result visually.

Visualize

The chart tools build a chart from a query result, then refine it one property at a time.

Tool What It Does

createWidget

Builds a chart from a previous query result. Supported types include line (trends), bar and column (comparisons), pie (distributions), and area (cumulative); you can name the type in your request. Responses can include a short narrative summary of the result. In clients that support interactive content, the chart renders live in the conversation; other clients receive only the narrative insights, without a rendered chart.

updateWidgetTitle

Changes the chart's title.

updateChartType

Changes the chart type, for example, from a column chart to a line chart.

rebindWidgetQuery

Points the chart at new data. Run buildQuery first.

updateWidgetSorting

Changes how the chart's data is sorted.

updateChartTrendForecast

Adds or removes a trend line or forecast.

updateWidgetStyle

Changes the legend, labels, and axes.

updateWidgetDataOptions

Changes the colors of series, bars, lines, and pie slices, and which measures show on the right axis.

updateChartMeasureTypes

In a combo chart, sets how each measure is drawn, for example, one measure as a line over columns.

Dashboards

The dashboard tools bring live dashboards into the chat. You can open an existing dashboard, build one from charts made in the conversation, and filter it. Each tool edits a draft dashboard inside the chat. Nothing is saved to Sisense.

Tool What It Does

loadDashboard

Opens an existing dashboard by its title or ID, as a draft in the chat.

createDashboard

Builds a new dashboard from charts made earlier in the chat.

addDashboardWidgets, removeDashboardWidgets, replaceDashboardWidgets

Add, remove, or swap widgets on the dashboard.

addDashboardFilters

Adds filters that you describe in plain language, for example, "last quarter, West region only."

addDashboardNarration

Adds an AI summary widget at the top of the dashboard.

updateDashboardTitle, updateDashboardRowHeight

Rename the dashboard or resize its rows.

In Claude, dashboards render live in the conversation only after an administrator adds Claude's content domain to the Sisense CORS allowed origins. See Interactive Charts and Dashboards in Claude.

Preview Data

Tool What It Does

getDataPreview

Returns the distinct values stored in a text column of a data source, so the agent can filter on the values in your data instead of guessed spellings. Available as of 2026.4.1.

Pulse

As of 2026.4.1, agents can work with the Pulses you created in the assistant.

Tool What It Does

listPulses

Lists your Pulses.

getPulse

Shows how a Pulse is defined.

listPulseEvals

Lists a Pulse's run history, including the outcome of each run.

getPulseEval

Shows the details of a single run.

getPulseEvalResults

Returns the values behind a run.

listPulseNotifications

Lists the notifications a Pulse sent.

evaluatePulse

Runs an existing Pulse right away and reports whether its condition is met, without waiting for its next scheduled run. If the run fires, the Pulse sends its notifications, including to its Slack, Zapier, and webhook destinations.

Note:

  • Agents cannot create a new Pulse or change an existing one, including its notification settings, through the MCP Server. Create and manage Pulses in the assistant.

  • The Pulse tools work with Pulses created through the assistant, not with classic Pulse alerts.

Note for Administrators:

Some tools were split into smaller tools. If buildChart, buildDashboard, or inspectPulse is turned off for a tenant, every tool that replaced it is hidden too:

  • buildChart: the chart tools under Visualize

  • buildDashboard: the tools under Dashboards

  • inspectPulse: the Pulse read tools under Pulse (all except evaluatePulse)

Tip: Improving Results.

Agents produce better answers when your data models are AI-ready: clear field and measure names, well-defined formulas, and curated perspectives. The more governed context your model carries, the more accurate the agent's queries and charts will be. See Optimizing Your Data Model for AI.

Using the MCP Server

Once connected, you work with your data in plain language. A typical session moves from discovery to a specific chart:

  1. See what you can query. Ask the agent to list your data sources, for example, "List my Sisense data sources."

  2. Inspect a model. Ask for the fields of the source you want, so the agent knows the available dimensions and measures, for example, "What fields are in Sample ECommerce?"

  3. Ask a question or request a chart. Describe what you want in business terms, for example, "Show total revenue by month for Sample ECommerce."

  4. Refine. Build on the result: change the chart type, add a dimension, or narrow the range.

  5. Bring it together in a dashboard. Combine the charts into a dashboard, or open an existing one, then filter it, for example, "Build a dashboard from these charts."

Example Requests

Discover

  • "List my Sisense data sources."

  • "What fields are available in Sample ECommerce?"

Ask and Visualize

  • "Show total revenue by month for Sample ECommerce."

  • "Show the top 10 products by sales."

  • "Compare sales by region."

  • "Show revenue by category as a percentage of the total."

  • "Show revenue comparison year over year."

Dashboards

  • "Open the Sales Overview dashboard."

  • "Build a dashboard from the charts we made, and add a summary at the top."

  • "Filter this dashboard to last quarter, West region only."

Tips for Good Results

  • Be specific. "Show total revenue by month as a line chart, sorted chronologically" beats "show revenue."

  • Refine step by step. Start simple, then add a trend line, a dimension, or a filter.

  • Use exact data source names. Data source names are case-sensitive. If a request fails, ask for the list of sources and copy the exact name.

  • One data source per chart. To combine sources, build separate charts.

  • Lean on common patterns: time series ("... over time"), top-N ("top 10 ... by ..."), comparison ("compare ... by ..."), and distribution ("... distribution by ...").