← Field Notes · July 8, 2026 · 4 min read · AIOProductOS Team

Connect your product data to Claude & Cursor over MCP

A step-by-step guide to connecting your product spine to Claude, Cursor, and other AI hosts over a hosted MCP server with OAuth — and what you can then ask.

Once you understand what MCP is, the natural next step is wiring your own product data into an AI assistant. This is a how-to: the exact steps to connect a hosted MCP server to Claude or Cursor over OAuth, and the questions that become answerable once you do.

What do you need before you start?

Two things. First, an AI host that speaks MCP over a remote server — Claude Desktop, Claude Code, Cursor, ChatGPT, Windsurf, and Cline all qualify in 2026. Second, an MCP server URL and an account to authorize against.

AIOProductOS hosts one at platform.aioproductos.com/api/mcp. It uses Streamable HTTP transport with OAuth 2.1, Dynamic Client Registration, and PKCE — which in plain terms means you add a URL and log in once, with no API keys to copy around. The server exposes 38 tools over your organization’s joined customer↔task↔revenue graph.

How do you connect the server to a host?

The flow is the same across hosts; only the menu names differ.

  1. Open the host’s connector or MCP settings. In Claude it is under Settings → Connectors; in Cursor it is the MCP servers panel.
  2. Add the server URL. Paste https://platform.aioproductos.com/api/mcp as a remote server. No JSON to hand-edit for the hosted flow.
  3. Complete the OAuth login. The host redirects you to authorize under your own account. Because the server supports Dynamic Client Registration, the host registers itself automatically — you do not pre-provision a client ID.
  4. Let the host discover tools. On connect, the host asks the server what it can do and pulls in all 38 tools with their descriptions and schemas. You do not configure them one by one.
  5. Ask something. The model reads the tool list and picks the right call on its own.

The whole thing is a two-minute settings task. If your data lives in one of the 100+ sources that feed the spine — Stripe, Intercom, GitHub, your tracker — it is already joined behind the server before you connect a single host.

What can you actually ask once it is connected?

This is the payoff. Because the server exposes a joined graph rather than one object, the assistant answers questions that normally take four tabs to piece together.

What you ask the assistantWhat it callsWhat used to be required
”Which $10K+ accounts asked for SSO, and what’s blocking it?”Cross-system read on revenue + feedback + tasksCRM → feedback tool → tracker, by hand
”Is this bug hitting paying customers or free users?”Join on the affected accountsError tracker → billing → CRM
”What did we ship last quarter that moved retention?”Outcomes joined to shipped workBoard → analytics → revenue dashboard

Contrast that with a single-product MCP: a feedback-tool server can summarize feedback, but it cannot tell you the revenue behind a request because that data lives in another system it cannot see. The difference in shape is the whole story, and it is covered in spine-MCP vs tool-MCP. You can also see the joined model on the spine page.

Is connecting your data safe?

The auth model is built for exactly this. OAuth 2.1 means you authorize the connection under your own login and can revoke it whenever you like — the host never holds a long-lived secret. Access is scoped to your organization and enforces the same row-level permissions as the app itself, so the assistant sees only what your account can see. And you bring your own model key: your prompts and results are not proxied through anyone else’s model. Data lives in your chosen region — EU or US residency — and the connection respects that boundary.

When is a custom API integration the better choice?

Here is the honest counter-case. The OAuth-and-a-URL flow is ideal for a human using an AI assistant interactively. It is not ideal for every scenario.

If you are embedding product-data lookups inside your own application, running a headless backend service, or need to shape responses to a fixed contract, you want to hit the underlying API directly rather than route through an interactive MCP host. MCP shines when a model is deciding what to call in a conversation; when your own code already knows exactly what it needs, the standard API is simpler and gives you tighter control over payloads, caching, and error handling. Reach for the custom integration there, and reserve the MCP connection for the assistant-in-the-loop workflows it was designed for.

The takeaway

Connecting product data to Claude or Cursor over a hosted MCP server is a settings task, not an engineering project: add a URL, authorize once, and the host discovers the tools. The value is not the connection itself — it is that you can now ask cross-system questions in plain language and get answers from live, joined data. If you are a PM, MCP for product managers covers what that changes in your week.

Want to see the joined graph respond before you connect anything? Browse a live workspace with no signup at platform.aioproductos.com/demo.

Frequently asked questions

How do I connect an MCP server to Claude or Cursor?

In the host's connector or MCP settings, add the server's URL — for a hosted server that is a single HTTPS endpoint. The host redirects you through an OAuth login to authorize access, then discovers the server's tools automatically. No API keys to paste, no per-tool configuration. Claude Desktop, Claude Code, Cursor, ChatGPT, Windsurf, and Cline all support this remote-server flow.

What is a remote MCP server?

A remote MCP server is one the vendor hosts and you reach over HTTPS, versus a local server you run yourself with a command like npx. Remote servers use Streamable HTTP transport and OAuth for auth, so connecting is just adding a URL and logging in once. AIOProductOS hosts one at platform.aioproductos.com/api/mcp with OAuth 2.1, Dynamic Client Registration, and PKCE.

Is it safe to connect my product data to an AI assistant over MCP?

The auth model is designed for it. OAuth 2.1 means you authorize the connection under your own account and can revoke it at any time; the host never sees a long-lived secret. Access is scoped to your organization and respects the same row-level permissions as the app. You also bring your own model key, so your prompts and data are not proxied through the MCP vendor's model.

What can I ask an AI assistant once my product data is connected over MCP?

Cross-system questions that used to require four tabs. Which paying accounts requested a given feature and what is blocking it. Whether a bug is hitting revenue or free users. What shipped last quarter that moved retention. Because the server exposes a joined customer graph, the assistant answers from real revenue, feedback, and task data in one call instead of summarizing a single tool.

Do I need to write code to connect my data over MCP?

No. Connecting a hosted MCP server to a host is a settings-panel task: add the URL, complete the OAuth login, done. Writing code only enters the picture if you want a custom integration against the underlying API instead of the standard MCP flow — which is the right call for embedded or headless use cases, but unnecessary for using an AI assistant interactively.

Keep reading

See the join on your own stack.

One record per customer — revenue, feedback, work, and code. Flat plans from $199/mo, every module included — a 14-day onboarding runway on your own data, then a 30-day money-back guarantee.