# Hypotize

> Hypotize is the first agentic Growth OS: the framework, MCP server, skills and plugin that turn your AI agent into a disciplined growth hacker. Your agent (Claude, ChatGPT, Codex, Cursor or any MCP client) reads and writes the experiment backlog, scores ideas, moves experiments through their stages and records outcomes and learnings, under rules the server enforces, so the team keeps one queryable history of what was tested and what it taught.

Hypotize works before and after an experiment runs. It does not assign traffic, serve feature flags or run A/B tests in application code: teams keep running tests in their own analytics and experimentation stack.

## What the Growth OS is made of

- Framework: hypothesis-first ideas, ICE, PIE, RICE or a custom scoring framework, enforced stages, and a measured result with a written learning at the end of every test.
- MCP server: 21 tools the agent uses to read and update the record.
- Skills: `hypotize-growth-experiments` (the method), `hypotize-weekly-review` (a read-only pipeline review) and `hypotize-backlog-import` (moving a spreadsheet or Notion backlog in batches of 50).
- Plugin: one install for Claude Code and Codex with the MCP server and the skills. Source: https://github.com/viluca94/hypotize-plugin. Install guide: https://hypotize.ai/skills
- App: the board, backlog and learnings the team works in, on the same record as the agent.
- Rules: an experiment cannot skip a stage and cannot close without a measured result and a written learning, whether a person or an agent is writing. The agent never touches billing or members.

"First" covers the experiment programme around the tests. Experimentation platforms such as GrowthBook, Statsig and Optimizely offer MCP servers to set up and read the A/B tests they run; Hypotize works alongside them.

## Connect an AI agent

- MCP endpoint: https://api.hypotize.ai/mcp (Streamable HTTP, OAuth 2.1 with PKCE, dynamic client registration and Client ID Metadata Documents)
- [MCP guide](https://hypotize.ai/mcp): how to connect Claude, ChatGPT, Codex, Cursor and other clients
- Codex: `codex mcp add hypotize --url https://api.hypotize.ai/mcp`, then `codex mcp login hypotize`
- Scopes: `hypotize:read`, `hypotize:write`, `hypotize:delete` (delete stays off unless the user turns it on at consent)

## What the agent can do (21 tools)

- Projects: list, get context and writing language, create, update, delete
- Experiments: list the backlog and pipeline, get one with votes, action plan and comments, create an idea, update, import up to 50 existing experiments at once, delete
- Scoring: ICE, PIE, RICE or a custom framework; vote and recalculate priority
- Lifecycle: move an experiment to its next stage, record the outcome, set the action plan, add comments
- Learnings: list outcomes and learnings across the project
- Every write tool takes an idempotency key, and project roles are checked on every call. Hypotize makes no server-side model calls.

## Shared workspaces

Every project belongs to a workspace with its own plan and members. New accounts start with a personal workspace and can join others by email invitation. Workspace members can create projects and edit every shared project. Private projects are available on Team and are visible only to explicitly invited people and workspace owners and admins. The highest workspace or project role applies.

Workspace owners and admins manage members and all projects, including private projects. Only the workspace owner controls billing, workspace deletion and ownership transfer. Project guests keep their own roles: contributors can read, vote and comment; viewers can read. Neither counts as a billable member.

`hypotize_projects_list` lists accessible projects across all workspaces and includes `workspace_id` and `workspace_name`. `hypotize_project_create` accepts an optional `workspace_id`: without it, creation uses the user's only workspace membership, or their personal workspace when they have several. The same 21 tools and idempotency keys apply.

## Pricing

- Free: $0, 1 member, 1 project per workspace, unlimited free contributors and viewers.
- Solo: $19.90/month per workspace, 1 member, unlimited projects, unlimited free contributors and viewers.
- Team: $39/month for up to 3 members, $10/month per extra member. Unlimited projects, private projects, and unlimited free contributors and viewers.
- Members are workspace owners, admins and members plus editor or owner project guests, counted once per person. Pending paid invitations reserve members. AI agents and MCP connections never count.
- Workspace overview, unlimited MCP clients and complete experiment history are available on every plan. Monthly billing only; no annual billing.

## Guides

- [Experiment memory](https://hypotize.ai/guides/experiment-memory)
- [ICE framework](https://hypotize.ai/frameworks/ice)
- [RICE framework](https://hypotize.ai/frameworks/rice)
- [Compare Hypotize with a spreadsheet or Notion](https://hypotize.ai/compare/experiment-tracker-spreadsheet-notion-or-hypotize)

## Comparisons

- [Hypotize vs experiment trackers](https://hypotize.ai/compare): none of the three products compared documents access for an outside AI agent, as of 15 October 2026.
- [Hypotize vs GrowthOrange](https://hypotize.ai/compare/hypotize-vs-growthorange)
- [Hypotize vs GrowthLab](https://hypotize.ai/compare/hypotize-vs-growthlab)
- [Hypotize vs Efestra](https://hypotize.ai/compare/hypotize-vs-efestra)

## Legal and support

- [Privacy policy](https://hypotize.ai/privacy)
- [Terms of service](https://hypotize.ai/terms)
- Support: hello@hypotize.ai