How do I use Cursor for SEO and to show up in ChatGPT?

Use Cursor as the hands, not the judge: put your SEO rules in .cursor/rules or AGENTS.md so every new page follows them, connect an MCP server in .cursor/mcp.json for live data and checks, and confirm each page on the published site before calling it done. Cursor writes pages well; it cannot see whether Google indexed them or AI assistants read them.

Facts

Cursor reads MCP servers from .cursor/mcp.json in a project and from ~/.cursor/mcp.json in the home directory, as of 2026-10-13. (Cursor docs: Model Context Protocol (MCP))
Cursor supports 3 MCP transports, stdio, SSE and Streamable HTTP, and OAuth for servers that require it. (Cursor docs: Model Context Protocol (MCP))
Cursor project rules live in .cursor/rules as .mdc files, and a plain .md file in that folder is ignored by the rules system. (Cursor docs: Rules)
Cursor has 4 ways to apply a rule: Always Apply, Apply Intelligently, Apply to Specific Files and Apply Manually. (Cursor docs: Rules)
Cursor supports AGENTS.md in the project root and in subdirectories. (Cursor docs: Rules)
AGENTS.md is an open format for guiding coding agents, used by over 60k open-source projects. (AGENTS.md: the open format for coding agents)

Does Cursor have an SEO feature?

No, Cursor has no built-in SEO mode; it does SEO through the rules you give it and the tools you connect. That is enough to write correct pages, but not to know whether they were indexed, read by AI crawlers or visited.

Where do I put SEO rules for Cursor?

Put them in a project rule in .cursor/rules, or in AGENTS.md if other coding agents also work in the repository. A rule scoped to your page files loads when Cursor touches them:

---
description: SEO rules for new content pages
globs: app/**/page.tsx
alwaysApply: false
---
- One H1 per page, phrased as the question the page answers
- Unique <title> and meta description; self-referencing canonical
- Content rendered on the server, not only after JavaScript runs
- JSON-LD only for what the page visibly says
- Add every new page to the sitemap
- Never change the home page or pages that already work

How do I connect an MCP server to Cursor?

Add it to .cursor/mcp.json for one project or ~/.cursor/mcp.json for all of them; remote servers take a url, and Cursor handles OAuth sign-in for servers that require it.

// .cursor/mcp.json (this project) or ~/.cursor/mcp.json (every project)
{
  "mcpServers": {
    "<name>": {
      "url": "<server-url>"
    }
  }
}

What can Cursor not check by itself?

Cursor sees your code, not the live site. These checks need the published page or outside data:

Question	Where the answer is
Does the page render with content without JavaScript?	Fetch the live URL, for example with curl
Is the canonical right?	The live HTML head; Google treats rel=canonical as a strong signal
Did Google index it?	Search Console
Did AI crawlers read it, did AI assistants send visits?	Server logs or an analytics tool that splits AI traffic

Step by step

Write the rules. Create a rule in .cursor/rules or an AGENTS.md with your page rules.
Connect the tools. Add the MCP servers you need to .cursor/mcp.json and sign in.
Ask for one batch of pages. Ask Cursor for a few new pages, each answering one question, without touching existing pages.
Review and deploy. Read the diff, then publish the batch together.
Check live. Open each published URL, check content, title and canonical, then watch indexing and AI visits.

Common mistakes

Saving the rule as a plain .md in .cursor/rules, where Cursor ignores it.
Accepting Cursor's summary that pages are live without opening the URLs.
Letting it rewrite the home page or pages that already bring traffic.
Putting API keys in a .cursor/mcp.json that is committed to the repository.

How easyIndex solves it

easyIndex works with a coding agent that has access to the website's repository: Claude Code, Codex, Cursor, Antigravity, Gemini CLI or any other MCP client. easyIndex connects to Cursor as an MCP server and gives it one step at a time; Cursor makes every change, and easyIndex never touches your site or repository.

Each page is audited when submitted and checked on the live site after publishing, and a step completes only on evidence easyIndex checks, not on Cursor's report. The dashboard then shows AI-assistant visitors per page, which pages AI crawlers read and Search Console data, for US$ 30 per website a month after a 7-day free trial.

Frequently asked questions

Can I use the same rules in Cursor and Claude Code?

Yes, through AGENTS.md: Cursor supports it, and Claude Code can read it or import it from CLAUDE.md.

Will Cursor get my site cited by ChatGPT?

No tool can promise that. Cursor can build clear, crawlable pages; whether ChatGPT cites them is decided by ChatGPT.

Should the rule always apply?

Scope it to your page files instead, so it loads when Cursor works on pages and stays out of other tasks.

Do I still need Search Console?

Yes. Only Search Console shows whether Google indexed each page and which searches show it.

Continue reading

Last verified on October 13, 2026.