Connect Claude or ChatGPT to your SEO data with MCP

The most natural interface to your SEO data might be the AI assistant you already talk to all day. Instead of learning our dashboard's every corner, you ask Claude "which of my clusters has no page yet?" and it answers from your actual data — then, if you let it, proposes what to do.

Maark makes that real through MCP, the Model Context Protocol: a standard way for an AI client to connect to an external tool server. We host the server; you add Maark as a connector in your AI client. Nothing to install on a server of your own.

How the connection works

The endpoint is the same everywhere: a single hosted URL your assistant connects to over streamable HTTP. There are two ways to authenticate, matched to how each client likes to connect:

• A scoped key (it looks like mk_…) for Claude Code and Cursor. You mint it once in your org settings, paste it into the client, and that is the connection.
• A guided sign-in (OAuth) for claude.ai and ChatGPT — you add Maark as a custom connector, approve it in a browser, and there is no key to copy. It uses OAuth 2.1 with PKCE, the modern, phishing-resistant flavor.

Once connected, your assistant can see your projects and read your Keyword Universe: pipeline status, brand context, the clusters that need pages, candidate pages for a cluster, the mapping evidence behind a recommendation, dead-link targets, and more.

Scopes: read, propose, operate

Every connection carries exactly one scope, and it decides what the assistant is allowed to do:

• Read — look, never touch. Every read tool, no writes.
• Propose — the assistant can draft changes, but write actions are clamped to a preview. It shows you what it would do; approvals still happen in Maark.
• Operate — the assistant can make real changes to your Keyword Universe: map a cluster to a page, move keywords between clusters, split a cluster, exclude off-scope terms.

There is a real authority ceiling here, not just a setting. A non-admin member of your org can only be granted read; propose and operate require an org admin to grant them. And even at operate scope, write actions default to a safe preview — to actually write, the assistant has to explicitly confirm, so a stray request cannot quietly mutate your data.

What it cannot do — by construction

This is the part we want to be unambiguous about, because "connect your AI to your data" makes people picture an agent with the keys to everything.

• It cannot publish to your site. Publishing always goes through the human review flow. There is no MCP tool that pushes anything live, at any scope.
• It cannot approve its own proposals. When the assistant suggests a mapping change or a new page, that lands as a proposal or an opportunity — a recommendation a human approves in Maark. The tool that grades and approves proposals is deliberately not on the connection at all, so an assistant cannot self-approve.
• It cannot wander into your other projects. A connection reaches only the specific projects you enable for it. A project that is not enabled for external access is invisible to the connection — there is no "all projects" backdoor, and asking about a project you did not grant returns the same "not found" as a project that does not exist, so the connection cannot even be used to probe what else you own.

Connections are rate-limited and every action taken over one is recorded, so you always have a trail of what ran, when, and under which scope.

The mental model

Think of it as handing your assistant a library card, not the keys to the building. It can read everything on your shelves, it can fill out a request slip for a change, and with the right card it can reshelve within the room you pointed it at — but it cannot walk into the next room, and it cannot publish a book with your name on the cover. You stay the editor.

The AI connections help articles have the exact setup steps for each client, and the Keyword Universe post explains the data your assistant is reading.