SEO Skill
Search Console, Google Analytics and keyword data for your AI agent.
At a glance
Not tested yet- GitHub stars
- 639
- Weekly downloads
- 6,494
- Last commit
- 2026-11-19
- Licence
- Apache-2.0
- Transport
- stdio
- Auth
- none
npx -y seo
What it does
SEO Skill is a Google Search Console MCP server and CLI. It gives an AI agent your real search data, such as clicks, impressions and positions from Search Console, visits from analytics sources, Bing data, Google update dates and a crawl of your site. It is for people who want their agent to work from their own numbers instead of generic advice or keyword estimates. It is free and open source.
Tools it gives your agent
seo next: where a site is in the SEO loop and the one step to do now, with its first jobs.seo report: your Search Console overview for--site, then the top rows of each section.seo page: one URL, its live page, its Google index status and its queries.seo compare: before and after a date, with Google updates.seo index: Google's indexing reasons for known URLs, labelled from live checks, and pages that lost their clicks.seo submit: ask Bing and others to crawl pages with IndexNow, or send them to Google with Index My Site.seo research: keywords, search results, competitors, backlinks and AI answer citations from your own key.seo data: raw Search Console or Bing rows, or Clicky and Simple Analytics landing pages.seo analytics: landing pages from Google Analytics, Clicky or Simple Analytics.seo crawl: technical issues and AI agent access across a site (CLI only).seo internal-links: internal links to add across a site or to one page (CLI only).seo lint: lines in a draft, title or description that read as AI-written, each with a fix.seo feedback: send a bug or idea about SEO Skill, with a proposed fix, to the maintainer.
Quick start
- Connect it to your agent. For Claude Code:
claude mcp add --transport http seoskill https://seoskill.dev/mcp
For Codex:
codex mcp add seoskill --url https://seoskill.dev/mcp
For other agents, add https://seoskill.dev/mcp as a remote MCP server.
- For crawls and Bing, which run on your machine, install the CLI:
npm i -g seo seo start
seo start signs you in, connects your agents and installs the skill.
- Sign in with Google. Pick the account that can see your Search Console. There is no password and no signup form.
- Ask it something real, such as "Why did clicks drop on example.com last month?"
Add it to Claude Code from a terminal:
claude mcp add seo -- npx -y seo
Or add this to .mcp.json in your project root (Claude Code) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"seo": {
"command": "npx",
"args": [
"-y",
"seo"
]
}
}
}Environment variables
The registry entry declares no environment variables.
Example prompts
- Why did clicks drop last month? Was it the core update?
- Which pages are close to page one, and what do they rank for?
- Is this page indexed? If not, why not?
- Can ChatGPT, Claude and Perplexity read my site?
What to watch out for
- You need a Google account that can see your Search Console.
- Keyword volumes and competitor data need your own DataForSEO or Ahrefs key.
- Sending pages to Google with Index My Site uses your own credits.
- Crawls and internal links are tools on the local MCP server only and need the CLI.
- The hosted server keeps your linked Google accounts and saved keys, encrypted, plus the issues list and business context your agent saves for a site. It does not keep your reports, Search Console rows or request logs, except what the paid weekly site audit keeps.
Not tested by tools4agents yet. Read the source repository before you install it.
Similar tools
Memory
A knowledge graph that persists facts across sessions, so an agent can recall context after the conversation ends.
DBHub
Token-efficient MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, ClickHouse, SQLite
PostgreSQL
Read only SQL access with schema introspection, so an agent can answer questions about your data without guessing column names.
Supabase MCP Server
Connects AI assistants directly to Supabase projects to manage database tables, query data, run migrations, and control edge functions.