Skip to content
MCP server

Sisense

Query governed Sisense data, build charts and dashboards from Claude, ChatGPT or Cursor

Install
Platforms
Web, API, self-hosted
Runs
Remotely
Version
1.0.0
Listing updated
today

Similar MCP servers

About Sisense

Sisense is an MCP server for analytics and data. It runs as a hosted remote server, so there is nothing to install locally.

The agent reaches data through Sisense, not directly. It works against your semantic model of metrics, terms and relationships, and every request runs as the signed-in user with their permissions, including row and column rules. Sign-in is OAuth 2.1 with PKCE and short-lived per-user credentials, with no shared key.

Agents can list data models and fields, translate plain-language questions into governed queries, turn results into charts, edit dashboards as drafts in chat, and keep results across steps. From 2026.4.1 they can also list and run Pulses. Dashboards are not saved to Sisense. It needs Sisense 2026.3.1 or later, is on by default on Managed Cloud and enabled by an administrator on self-hosted installs. The AI tools need Cloud-Linked Features and a model provider.

Install

Run in a terminal

claude mcp add --transport http mcp https://mcp.sisense.com/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.sisense.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.sisense.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.sisense.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://mcp.sisense.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.sisense.com/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Tools this server provides (3)

Taken from the project documentation; the running server may differ.

buildQuery
Turns a plain-language request into a governed query.
getDataSources
Lists data sources you can access.
getDataSourceFields
Inspects fields and measures of a data source.

What it does

Governed queries
Natural-language questions become queries against your semantic model.
Per-user access
Calls run with the signed-in user's permissions.
Live charts
Charts render inside supporting clients.
Draft dashboards
Edit dashboards in chat without saving.
Pulse review
List and run existing Pulses.
Admin control
Managed under System Configuration > MCP.

Good for

  • Ask a metric question in chat
  • Build a chart and refine it
  • Check a Pulse condition on demand

Pricing

Pricing unknown

Part of Sisense tiers (Launch, Grow, Enterprise); prices not published

Prices change. Check docs.sisense.com before you buy.

Sisense FAQ

What version is needed?

Sisense 2026.3.1 or later.

Does it save dashboards?

No; dashboards are edited as drafts.

What do AI tools need?

Cloud-Linked Features and an LLM provider.

Which clients are validated?

Claude, ChatGPT and Cursor.

How do I add Sisense to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://mcp.sisense.com/mcp

What are the best alternatives to Sisense?

The closest alternatives to Sisense are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, dashboard-icons, Tapetide - Indian Stock Market MCP and World Monitor.

Where this comes from

  • Description: written from the project's website.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers