keyword_researchLABSCO SUMMARY
The SEO check that happens while you are still writing.
Keyword research, SERP reading and on-page grading are normally three tools and a context switch away from the draft. Having them answer inside the draft is what makes them get used at all.
What it is
A self-hosted MCP server for SEO and marketing research. Four tools covering keywords, results pages, links and on-page work.
What you get
- Keyword opportunities researched — search volume indicators, difficulty, related terms and content suggestions
- A search results page analysed: top ranking pages, the content patterns among them, and an assessment of the ranking opportunity
- A backlink profile analysed — referring domains, anchor text, link quality and link building opportunities
- On-page SEO analysed for a page — keyword density, readability, structure, meta tags and specific improvements
Requirements
Clone the repo, run it with Bun, and supply your own OpenAI API key and an admin secret you choose. The server mints its own API keys through /api/keys/provision; send the key as an x-api-key header to http://localhost:4201/mcp.
Setup effort
Build from source — git clone https://github.com/ezbiz-services/mcp-seo-marketing.git
USE CASES
Deciding what a page should target
Research the keyword's volume, difficulty and related terms before committing the draft to one.
Working out whether you can rank at all
Analyse the SERP for the term and read the opportunity assessment against who is already there.
Grading the page you just wrote
Run on-page analysis for keyword density, readability, structure and meta tags, and take the specific fixes.
Understanding why a competitor outranks you
Read their backlink profile — referring domains, anchor text and link quality.
Planning a content brief end to end
Research the keyword, analyse the SERP for it, then check what links the current winners have.
4 tools
Listed in project docs. Your client may show a different list.
analyze_serpcheck_backlinksoptimize_contentBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
- Bun
- An OpenAI API key
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
This one is built from source rather than installed with a single command.
Server setup
git clone https://github.com/ezbiz-services/mcp-seo-marketing.git
cd mcp-seo-marketing
bun install
cp .env.example .envSet OPENAI_API_KEY and ADMIN_SECRET in .env
bun run server.tsLeave that server running, and in a second terminal mint the API key your client sends as x-api-key:
curl -X POST http://localhost:4201/api/keys/provision -H "x-admin-secret: <YOUR_ADMIN_SECRET>" -H "Content-Type: application/json" -d '{"email":"<YOUR_EMAIL>","tier":"business"}'MCP Clients
Cursor
{
"mcpServers": {
"seo-marketing": {
"url": "http://localhost:4201/mcp",
"headers": {
"x-api-key": "<YOUR_API_KEY>"
}
}
}
}