Sigma Computing MCP Server
Connect to the Sigma Computing MCP server to manage workbooks, export and email data, inspect schemas, and administer members and workspaces using AI agents on Gumloop, Claude, or Cursor.
Try Sigma Computing now
Type what you want done. Sign in and run it live with an AI agent.
|
Sigma Computing
Installation
Get StartedCreate a Gumloop Account
To use this MCP, you need a Gumloop account. If you don't have one yet, you can create one for free.
Copy Your Server URL
Copy your MCP server URL and add it to your client. You'll be prompted to authorize on first use.
Tools (45)
List Workbooks
List workbooks with optional pagination
Get Workbook
Get workbook details by ID
Create Workbook
Create a new workbook
Duplicate Workbook
Create a copy of an existing workbook
List Workbook Pages
List pages in a workbook
List Workbook Elements
List all elements in a workbook
Get Workbook Schema
Get the schema of a workbook including columns and element structure
Get Workbook Sources
Get data sources connected to a workbook
List Workbook Queries
List SQL queries in a workbook
Export Workbook
Trigger a data export from a workbook. Returns a queryId to use with download_workbook_export
Download Workbook Export
Download a previously exported workbook file to Gumloop storage using a queryId from export_workbook
Send Workbook
Send a scheduled export of a workbook via email
What is Sigma Computing MCP?
The Sigma Computing MCP server gives AI agents access to your Sigma Computing analytics environment. That means agents can list and create workbooks, duplicate and tag them, export workbook data as CSV, XLSX, JSON, PDF, or PNG, email those exports to stakeholders, inspect a workbook’s pages, elements, schema, data sources, and SQL queries, administer members, teams, and workspaces, grant access, and health-check the warehouse connections behind your dashboards. It works across the core Sigma objects: workbooks, members, teams, workspaces, data connections, and templates.
If your data team spends time exporting dashboards by hand, emailing the same weekly reports, documenting workbook sources and queries, or chasing down who has access to what, an AI agent can take over a lot of that busywork. Describe what you need, and your AI agent will handle the BI operations for you.
MCP stands for Model Context Protocol. It’s an open standard that gives AI agents a way to connect to external tools and services. Instead of minting OAuth client-credentials tokens against the Sigma API, handling token refresh and pagination, and parsing JSON responses yourself, you add your Sigma API client ID, client secret, and cloud URL to Gumloop once. After that, you can run your Sigma reporting and administration just by chatting with your AI agent.
Related MCP servers
Tableau MCP Server
Interact with Tableau to access views, workbooks, datasources, and Pulse metrics
Looker MCP Server
Interact with Looker Enterprise dashboards and analytics content
Databricks MCP Server
Manage Databricks clusters, jobs, and job runs
Snowflake MCP Server
Interact with Snowflake data warehouse for executing SQL queries, managing tables/databases, and accessing data
Google BigQuery MCP Server
Query and manage BigQuery datasets, tables, and execute SQL
Hex MCP Server
Interact with Hex to manage projects, runs, collections, data connections, users, and groups
What you can do with Sigma Computing MCP on Gumloop
Create and manage workbooks
List and open workbooks, create new ones, duplicate an existing workbook into another folder, add tags to organize them, and pull a workbook’s full version history. Your AI agent can stand up and label reports without you clicking through the Sigma UI.
Export and download workbook data
Trigger a data export for a workbook, page, or element as CSV, XLSX, JSON, PDF, or PNG (up to roughly one million rows), then download the finished file into Gumloop storage. This two-step export and download pipeline lets an agent pull live warehouse data and hand it to the next step.
Email workbook reports to stakeholders
Send a workbook export by email to a list of recipients with a subject, message, and file type of your choosing. Your AI agent can deliver the Monday morning report so nobody has to remember to export and attach it.
Inspect workbook structure, sources, and queries
Read a workbook’s pages, elements (tables, charts, and more), column schema, connected data sources, and the SQL queries behind it. This deep introspection lets an agent document a dashboard, trace its data lineage, or flag where two reports pull from different sources.
Administer members and account types
Look up the current API user, list account types and custom user attributes, search members, read member details, invite new members, update profiles and account types, deactivate members, and see which teams a member belongs to. Onboarding and offboarding become a request instead of a checklist.
Manage teams and membership
List teams, read team details and members, create teams, update a team’s name, description, or visibility, add or remove members, and delete a team. Your agent can keep team rosters in sync with your org.
Organize workspaces and grant access
List, read, create, update, and delete workspaces, list a workspace’s permission grants, and grant member or team access to workspaces and individual workbooks at view, explore, organize, or edit levels. An agent can audit who can reach what and provision access as people join.
Monitor data connections and provision from templates
List and inspect warehouse connections, test whether a connection is live, and look up a database, schema, and table path inside a connection. List and read workbook templates and stamp out a new workbook from one for fast, standardized analytics.
How to connect the Gumloop Sigma Computing MCP Server
- 1
Create a free Gumloop account
Sign up at gumloop.com. No credit card required.
- 2
Add the Sigma Computing MCP server
Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.
- 3
Start using Sigma Computing in your AI workflows
That's it. Your AI agent can now manage workbooks, export and email data, inspect schemas and queries, and administer members, teams, and workspaces. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.
Sigma Computing MCP use cases
Automated report distribution for data teams
On a schedule, a Gumloop agent can export a workbook to PDF or XLSX, email it to a recipient list with send_workbook, and post a short summary plus a link to a Slack channel. Stakeholders get the numbers on time without an analyst exporting and attaching files by hand every week.
Warehouse data extraction for analytics engineers
An AI agent can trigger a workbook export of up to roughly one million rows, download the file into Gumloop storage, and pass it to the next step for transformation, loading into Google Sheets, or feeding a downstream model. The two-step export and download flow turns a live dashboard into a reusable data feed.
Workbook documentation and data lineage for analysts
Point an agent at a workbook and it can read the pages, elements, column schema, data sources, and embedded SQL queries, then write a clean documentation page to Notion or Google Docs. Teams get up-to-date docs and a lineage trail without anyone reverse-engineering a dashboard by hand.
Access governance and onboarding for BI admins
When a new analyst joins, an agent can create the member, add them to the right teams, and grant view or explore access to the workspaces and workbooks they need, then list workspace grants to confirm the result. The same agent can audit existing grants across workspaces for a periodic access review.
Self-service dashboard provisioning for operations teams
An agent can list available templates and create a new workbook from the right one into a chosen folder, tag it, and email the owner that their dashboard is ready. Standardized reports get spun up on demand instead of waiting in a request queue.
Why use Gumloop for Sigma Computing MCP
Your Sigma credentials, stored securely
Most Sigma MCP servers you’ll find on GitHub make you mint OAuth client-credentials tokens and write code to handle authentication, token refresh, pagination, and rate limits. With Gumloop you add your Sigma API client ID, client secret, and cloud URL once, stored securely, and the server refreshes the short-lived access token for you. No env vars, token minting, or coding against the Sigma API necessary.
Works with multiple MCP clients
Use the Sigma Computing MCP server endpoint in Claude Desktop, Cursor, or directly inside Gumloop agents. Same server URL, works with any MCP client.
Chain Sigma Computing with 100+ other integrations
Combine Sigma Computing with Slack, Gmail, Google Sheets, Notion, and other MCP integrations in a single AI agent. Pull a workbook export from Sigma, process it with an LLM, and write the result to a sheet, a doc, or a Slack channel.
Enterprise-grade and scalable
Built for teams, with role-based permissions and dedicated support for Pro users. For details on Gumloop’s security practices, see trust.gumloop.com.
Pricing includes a free plan
You can test the Sigma Computing MCP integration on Gumloop’s free tier before committing. Paid plans start at $37/month with higher usage limits and additional features.
Frequently asked questions
Ship Sigma Computing agents in minutes
Connect any AI agent to 100+ MCP servers, zero setup.