Gemini CLI is fast and cheap to run in a loop, which makes it a good SEO worker once it has data. Connect omnifamous and it can research keywords, pull traffic and backlink data, and check whether Gemini and other engines mention your brand.
Live now: the MCP server, the free AI visibility audit and the keyword tools. Gemini CLI wants httpUrl rather than url in ~/.gemini/settings.json. Using url silently selects the deprecated SSE transport, which is the single most common reason a Gemini MCP setup looks connected and returns nothing.
Gemini CLI wants httpUrl rather than url in ~/.gemini/settings.json. Using url silently selects the deprecated SSE transport, which is the single most common reason a Gemini MCP setup looks connected and returns nothing.
Paste this in and it reads our skill, then writes its own config in the format Gemini CLI expects.
Read https://omnifamous.com/mcp/skill.md and set up the OMNIFAMOUS SEO MCP server for this project, then use it to audit my site's search and AI visibility.
~/.gemini/settings.json
{
"mcpServers": {
"omnifamous": {
"type": "http",
"httpUrl": "https://mcp.omnifamous.com"
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"omnifamous": {
"type": "http",
"httpUrl": "https://mcp.omnifamous.com",
"headers": {
"Authorization": "Bearer sk_your_workspace_key"
}
}
}
}Gemini CLI expects httpUrl for a streamable HTTP server. Use url only for the deprecated SSE transport.
Every surface of the engine, as tools your agent can call mid-conversation.
One block in ~/.gemini/settings.json using httpUrl, then /mcp auth to sign in. Gemini CLI gets the full tool catalog: keyword ideas, traffic estimates, backlinks, competitor gaps, page checks and AI visibility.
Check whether ChatGPT, Claude, Gemini and Perplexity mention a brand on a sample of questions, and read your saved AI Visibility monitoring results: answers, cited domains and trend.
Anonymous AI visibility audit and keyword research at /tools/seo-audit, no login required.
The page-check and speed-audit tools also have plain HTTP endpoints, so you can script them without an MCP client. Keyword, traffic, backlink and gap data is MCP only.
Whichever way you connect, the omnifamous engine does the heavy lifting for your brand.
Audits your AI visibility so you can see which prompts name your brand and which name a competitor.
Researches winnable keywords for your market with real search data behind every pick.
Compares your keywords and backlinks against a competitor so you know what to write next.
With the AI Visibility plan, reads your scheduled monitoring results so you can prove the trend as content ships.
Four steps. You stay the editor, the engine handles the rest.
Add the server to Gemini CLI. One block in ~/.gemini/settings.json using httpUrl, then /mcp auth to sign in.
Ask in plain language. The agent picks the tools, so you never call one by hand.
Review the research. Every number comes from a live data provider, not from the model.
Decide what to ship. You stay the editor while the tools supply the numbers.
Everything you need to know about how the engine does the work for you.
Yes. One block in ~/.gemini/settings.json using httpUrl, then /mcp auth to sign in. Once it is connected, Gemini CLI can research keywords, estimate traffic, check backlinks, compare keyword gaps against a competitor, inspect pages, and check whether ChatGPT, Claude, Gemini and Perplexity mention your brand.
Gemini CLI wants httpUrl rather than url in ~/.gemini/settings.json. Using url silently selects the deprecated SSE transport, which is the single most common reason a Gemini MCP setup looks connected and returns nothing. The exact config block for Gemini CLI is on this page, ready to copy.
Almost always the url versus httpUrl mistake. Gemini CLI treats url as the deprecated SSE transport and httpUrl as streamable HTTP. Use httpUrl, as in the block on this page, then run /mcp list to confirm.
Yes. ai_visibility_run_scan covers ChatGPT, Claude, Gemini and Perplexity, and a prompt monitor (monitor_prompts_create) includes google_ai_overview in its default engines. monitor_prompts_run_now fires one run on demand, charged 300 credits per engine x region answer that lands (times the engine's multiplier on expensive model APIs).
Because it will make the numbers up. Language models routinely invent search volumes, difficulty scores and competitor rankings that look plausible and are wrong. Every number our tools return comes from a live data provider or your own workspace.
Page inspection and robots/sitemap checks are free without a key, broken-link checks are free with a key, and reads of your saved AI-visibility data cost no credits (they need the AI Visibility plan). Tools that buy live market data spend workspace credits at a published per-call price, charged only on a successful answer. There is no signup credit grant.
Two ways. On demand, ai_visibility_run_scan asks ChatGPT, Claude, Gemini and Perplexity three questions about your domain and reports whether your brand appears. For tracking, the AI Visibility plan scans your own prompts on a schedule, and the workspace read tools return those saved answers, cited domains and trends to your agent.
Still have questions? Talk to us
Same engine, wherever your agent lives. See how it connects to each runtime.
Connect the server and it works from real keyword, SERP, backlink and AI-visibility data instead of numbers it invented. Start with the free audit, no account and no card.
Run my free auditNo credit card required. Results in under 5 minutes.Tell us about your site so we can tailor your OMNIFAMOUS demo. Next, you'll choose a time that works for you.