CLI and MCP server

Your marketing engine. In your AI agent's hands.

Your Google rankings and AI citations, run by RankControl. Claude, Codex, or any AI agent can drive all of it: check visibility, plan content, publish. Setup takes two minutes.

01

Install the CLI

npm install -g rankcontrol

02

Authorize your workspace

rankcontrol login

03

Give it to Claude Code

claude mcp add rankcontrol -- npx rankcontrol mcp

Claude Desktop, Cursor, and Codex take the same server. Or skip MCP and install the agent skill: npx skills add rankcontrol/rankcontrol. Setup guide

Agent session

Done
Checked visibility
Planned 12 titles
You approved 8
Publish dry run
Confirmed live

MCP tools

64

one command to connect

Dry run first

Your AI assistant can read your code, draft your email, and plan your week. But your marketing platform is still a browser tab it cannot touch. Plug it in.

One command connects RankControl to Claude, Cursor, or any agent that speaks MCP. Your workspace, your rules, in every tool.

64 tools, full loop

From visibility check to published article

npx rankcontrol mcp · 64 tools

get_visibility_score

Your overall AI visibility number, right now.

get_visibility_trend

Start here

Daily score history from your weekly citation checks.

list_citations

Recent checks per AI model, cited or not.

get_overview_funnel

AI crawls and AI visits, last 30 days.

get_planning_capacity

How many content slots are left this month.

plan_content

Propose article titles. Nothing gets scheduled.

commit_planned_titles

Approve reviewed titles onto the calendar.

list_content

Every article with its current status.

publish_content

Dry run by default. Confirm to go live.

list_jobs

What the agents are working on right now.

These ten run the core loop. Brand memory, repurposing, link building, outreach, social, and reports round out the 64. Browse them all in the docs

Included in the plan. Nothing extra to buy.

Start Free Trial

How it works

Your workspace, wherever you work

Use it as a plain command line tool, hand it to your AI assistant, or wire it into your own agents. The rules stay the same everywhere.

01 / Terminal

The dashboard, minus the dashboard.

Check your funnel and what every agent is working on without leaving the command line. Connect once, and every number you see in the dashboard answers from the same live workspace.

02 / MCP

Ask your assistant. Get your real numbers.

Add RankControl to Claude Code, Claude Desktop, Cursor, or Codex in about two minutes. Your assistant answers from your live data instead of guessing, and can plan next steps the moment it spots a gap.

03 / Guardrails

Let agents do the work. On your terms.

Agents plan titles, write drafts, and prep outreach on their own. They act only with the access you connected, and your plan limits apply the same in every tool.

Works Where You Work

From Claude to Cursor to a plain terminal or your CI. One package covers every place you already work.

2 minto connect

Keys You Control

One browser approval connects your workspace. Revoke access anytime, and mint read-only keys in Settings for CI or vendors.

1click to revoke

Same Rules Everywhere

Dashboard, terminal, or agent: it is the same workspace with the same plan limits in every tool.

1set of rules, every tool

A keyboard, an approved checklist, and a key on a desk

This morning

12 titlesproposed

Auto-published

0ever

“Our agent checks citations every morning and drafts the next batch of titles. I review them over coffee and approve. It runs like an ops team that never sleeps.

64

tools your agents can call

1

command to connect any of them

0

actions outside the access you set

Common questions

Before you connect

Can an agent publish without me?

No. Publishing is a dry run by default, so nothing goes live until you confirm it. Planning works the same way: your agent proposes titles, you approve them. Approval always stays with you; no connected tool can skip it.

Which AI tools does it work with?

Anything that speaks MCP: Claude Code, Claude Desktop, Cursor, and Codex, plus any custom agent. The CLI also works in a plain terminal or CI, no AI required.

Do I need to be a developer?

No. Connecting is one copy-paste command, and login is approved in your browser. And if you never touch a terminal, everything here is also in the dashboard.

Is my data safe?

CLI access is owner-only and you can revoke it in Settings anytime. For CI or third parties, mint scoped or read-only keys there instead.

Does it cost extra?

No. The CLI and MCP server are included in the one RankControl plan, same data, same limits, same everything.

Free research report

The State of AI Visibility in 2026

25-page research document covering how brands get cited by ChatGPT, Perplexity, Claude, and Gemini, with data, benchmarks, and actionable strategies.

No spam. Unsubscribe anytime.

RankControl Research

The State of AI Visibility in 2026

25 pages · data + benchmarksFREE

ChatGPT · Perplexity · Claude · Gemini

Explore the rest of the platform

Give your AI tools the keys. Take them back anytime.

One command connects your terminal, Claude, or Cursor. Free for your first 30 days.

See the Live Demo