Flow-based workspace

Glacier

AI-native workspace for technical teams.

Kanban board. Linked docs. MCP-first.
Built for the way small teams actually work with AI.

app.getglacier.ai
Queue2

MCP write tool for docs

Cycle autorollover logic

Active3

Landing page redesign

API key management UI

Waterline visual language

Done2

Full-text search with Postgres FTS

Command palette (⌘K)

The problem

Every workspace was built before AI joined the team.

Linear is fast but siloed. Notion is flexible but slow. Neither assumes Claude is reading your board.

What you see: a clean Kanban board and a linked doc editor.

waterline

What’s underneath: an MCP server that exposes your entire workspace to Claude.

What glacier is

Kanban Board

Flow-based, not sprint-based. WIP limits built in. Cycle time visible at a glance.

Column types, cycle auto-rollover, drag-and-drop at any scale.

Docs & Knowledge

ProseMirror editor. Docs live inside projects, linked to cards.

Claude receives structured markdown — not raw JSON.

MCP Server

Read and write tools. Claude Code, Claude Desktop, any MCP agent.

Per-user API keys. Native protocol. No plugins, no wrappers.

Who it’s for

Built for one kind of team.

Small technical collectives — 2 to 10 people — where AI is already in the daily workflow. Teams where Claude Code is open next to the terminal. Where context moves faster than standups.

Built for ourselves. Used across three teams and five active products at Black Bear Studio.

Dogfood

We build on what we ship.

Black Bear Studio runs on Glacier internally. Every friction point becomes a fix. Every missing feature becomes a card.