Semrush in Codex: A Real Keyword Research Call via BrowserAct MCP

Description and use

The author integrated Semrush keyword queries into Codex via BrowserAct MCP, receiving structured data for "OpenAI Codex" and search result links, enabling content decisions without manual copy‑paste.

Problem

The author wanted to eliminate manual copying of Semrush reports into Codex content briefs and make keyword research directly available within the conversation.

Outcome

The MCP call returned a keyword overview for "OpenAI Codex" with 14,800 monthly search volume, 94 keyword difficulty, and five related search‑result links, enabling the author to evaluate the topic’s relevance and refine the content angle.

Workflow

• 1. Copy the ready‑built Semrush Bot template into a BrowserAct account. 2. Import Semrush cookies in Browser settings. 3. Publish the Bot to expose it as an MCP tool. 4. In Codex, invoke the MCP tool with the keyword "OpenAI Codex" and database "United States". 5. Receive the keyword overview and search‑result links in the Codex session. 6. Use the returned data to inform the content brief and decision making.

Evidence

I had Semrush data in one tab and a content brief taking shape in Codex. To see whether I could stop moving reports by hand, I tested an existing BrowserAct Semrush Bot as an MCP tool.

Source

The task finished successfully on October 27, 2026. It returned one exact‑match keyword overview and a separate section containing five search‑result links.

Source

The returned page links included github.com/openai/codex, openai.com/codex/, openai.com/index/introducing-codex/, platform.openai.com/codex, and learn.chatgpt.com/docs.

Source

The business value I see in making an existing subscription callable.

Source