What we read
Your plan, plays and business context, exposed to the assistant you already use — only when your assistant asks for it.
What changes in your plan
Claude, ChatGPT, Cursor and Codex can read your plan and help you ship the work, with your positioning and numbers already in context.
- Ask your assistant to draft a play using your real plan
- Pull the week's priorities into whatever you are already working in
- Keep one source of truth instead of re-explaining your business
- Write copy that matches how your site already describes you
How to connect
Copy the MCP endpoint from Integrations into your assistant's config.
What we never do
The assistant reads what your workspace already holds. It cannot post anywhere, and paid tools stay gated to your plan.
Connecting it, step by step
Add the endpoint to your assistant
Once connected, you stop pasting context into every conversation.
- Open Integrations and copy your MCP endpoint
- Add it to Claude, ChatGPT, Cursor or Codex as a connector
- Approve access the first time your assistant asks
- Ask it for this week's plays to check the connection
- Effort
- Two minutes
- Payoff
- Your assistant working from your real plan
Before you start
Which assistants work?
Anything that speaks MCP — Claude, ChatGPT, Cursor and Codex are the ones we document.
Can the assistant change my plan?
It works within your workspace permissions, and you approve the connection. You can revoke it at any time.
Does it cost extra?
No. It is included; some tools require an active plan.
Do I have to connect anything?
No. Every play still spells out the steps by hand. Connecting just makes the ranking sharper.
Can I disconnect later?
Yes, from Integrations, and we stop reading immediately.
See your own ranked plan