Skip to main content
Connect Glood to the AI assistant you already use. Ask it how conversion did last week, what your agents found overnight, or which of your best-converting products are out of stock — it reads your Glood data directly and answers with the same figures the dashboard shows. The assistant’s own model and its cost stay yours. The data, and the permissions on it, stay ours.
A connection carries your own role and nothing more. It can do what you can do in the dashboard, in the organizations you chose to share — and it cannot be talked into more than that by anyone, including you.

​
Before you start

You need a Glood account and membership in at least one organization. When you connect, you choose which of your organizations the assistant may reach. It is not all of them by default, and never more than you tick.

​
Where to go next

Connect your assistant

Claude, ChatGPT, Codex, Gemini CLI, opencode — pick yours and paste one URL

Connect any MCP client

The endpoint, the transport, and how OAuth works with no key to paste

Install the skills

Two skills that teach your assistant how to operate Glood well

Tools reference

All fourteen tools, what each answers, and what it needs

Using it

What to ask for, and how to read the answers you get back

Access and privacy

What it can reach, what it refuses, and how to revoke it

​
What it is not

This is not a chatbot bolted onto the dashboard, and it is not a separate product with its own data. It is the dashboard itself, reachable as tools: the assistant runs the same code the screen does, so a figure in chat and a figure on the page cannot disagree. A short list stays on the dashboard deliberately — signing in, two-factor, creating organizations, authoring roles, and changing what a connection can reach. See what it will not do.