Skip to content
← Tools / Skills
ToolCount/10 trustVerified

Count

A collaborative, reactive canvas that replaces the data notebook.

Visit official site →

About

Count is a UK analytics platform founded in 2016 that calls itself a collaborative and reactive data whiteboard. Instead of linear notebooks, analysts break complex SQL and Python queries into interconnected cells on an infinite canvas, with visuals and sticky notes alongside. The company has been moving it toward an agentic canvas: SQL plus Python plus visuals over connected warehouses, with MCP connectivity and a public API, explicitly positioning it as 'bye-bye notebooks, hello canvas.'

Comparison directories list it at roughly $34 per editor per month with integrations for BigQuery, Snowflake, Postgres, MySQL, and Redshift, and note any canvas can become an interactive report or slideshow. The reactive-cell model is a real differentiator from Metabase and Mode, though I could not hands-on verify the agentic/MCP claims, so treat those as provider-claimed.

What it can do

  • Infinite canvas for SQL and Python analysis
  • Reactive interconnected cells
  • Visualizations and sticky notes
  • Turn canvases into interactive reports or slideshows
  • Collaborative real-time editing
  • Warehouse integrations (BigQuery, Snowflake, Postgres, MySQL, Redshift)
  • Agentic canvas with MCP connectivity (per vendor)

Setup

  1. Sign up at count.co.
  2. Connect your data warehouse (BigQuery, Snowflake, Postgres, MySQL, Redshift).
  3. Drag SQL and Python cells onto the canvas and build visuals.
  4. Share canvases as interactive reports or slideshows.

Prerequisites

A cloud data warehouse or SQL database.

Use cases

data-explorationbusiness-intelligencesql-assistantdata-visualizationcollaboration

Works with

Trust score — 6/10

/10 trustVerified

Scored 6/10 (TIER metrics, metrics-v1). Evidence: founded 2016 (UK), operating site count.co verified live; ~$34/editor/mo pricing and warehouse integrations consistent across directory listings; 16 ratings on SourceForge. Strengths: decade-long operation, genuinely distinct canvas model vs notebooks, recent agentic/MCP positioning. Docked for: (1) small public rating base and no funding/adoption numbers I could verify; (2) agentic and MCP claims are provider-stated, untested. License: proprietary.

How the trust score is built

Full methodology →
Adoption · stars/downloads, log-scaled vs peers
6.0/10
Maintenance · recency, releases, issue load
7.0/10
Openness · license + docs
6.0/10
Manual review · sanity read + red-flag check
6.0/10
  • · Founded 2016, UK (Slashdot vendor data); count.co verified live
  • · ~$34/editor/mo pricing and BigQuery/Snowflake/Postgres/MySQL/Redshift integrations per directories
  • · 16 SourceForge ratings; agentic canvas + MCP positioning via third-party commit notes
  • · Agentic/MCP claims are provider-stated, untested

Sources

Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.