For developers and AI agents
Use RankMeOff from Claude, Cursor, and Codex
RankMeOff runs a Model Context Protocol server at https://rankmeoff.com/mcp. Connect it to any MCP client so your agent can run supported search-result checks and URL-processing tasks, verify backlinks, use free diagnostics, and review task reports with the same account and token balance as the web app.
Requirements
MCP access is included with any RankMeOff token pack. Create an MCP key from AI agents in your account (sign in or create an account first). Free diagnostic tools are available inside the app with a RankMeOff account; browse the tool descriptionsbefore creating an account.
Paste this into your AI agent
Sign in and create a key from AI agents first, then replace YOUR_RMO_KEY below with it before pasting this into Claude Code, Cursor, or any chat-based agent.
Connect the RankMeOff MCP server so you can use my RankMeOff account. Server URL: https://rankmeoff.com/mcp Transport: Streamable HTTP Auth header: Authorization: Bearer YOUR_RMO_KEY If you are Claude Code, run: claude mcp add --transport http rankmeoff https://rankmeoff.com/mcp --header "Authorization: Bearer YOUR_RMO_KEY" Otherwise add it to your MCP config file using the URL and header above. Then call the free get_account and get_pricing tools to confirm the connection and explain the available tools and current rates. Rules: before any tool that spends tokens, call estimate_cost, explain the billing mode and total, and ask me to confirm. Pass the quoted total as max_tokens. Never retry a failed spend automatically, and never open or pay a top-up link yourself.
Choose the right tool
For search-result visibility, use create_index_check. To process URLs, use create_indexing_task; Google uses fetch-and-verify, while eligible verified Bing/Yandex hosts may receive IndexNow. To check links on source pages, use create_backlink_check. For redirects, noindex, HTTP status, or sitemap extraction, use the free diagnostic tools. These checks are not complete index lookups and do not guarantee indexing.
Before a paid task, call estimate_cost, explain the total and billing mode, and wait for the user’s confirmation. max_tokens is a hard total-spend ceiling; if it is below the estimate, nothing is charged.
Tools
Every spending tool requires a max_tokens budget. If the real cost is higher, nothing is charged and the tool returns a quote instead.
get_account
Token balance, this key's daily cap, and today's spend.
freeget_pricing
Live token costs and which paid products are enabled.
freeestimate_cost
Quote a job before running it; nothing is charged. Explains result-based versus flat billing.
freecheck_redirects / check_noindex / check_404 / check_5xx
Single-URL diagnostics, same checks as the free web tools.
freeextract_sitemap
Fetch and parse an XML sitemap or sitemap index.
freecreate_index_check
Check URL visibility in Google, Bing, or Yandex search results. This is a time-specific observation, not a complete index lookup.
free to quote, then per URLcreate_backlink_check
Verify source URLs actually link to a target URL.
per donor URLcreate_indexing_task
Process URLs with fetch-and-verify, or send an IndexNow notification for eligible key-file-verified domains. Neither method guarantees indexing.
per result-confirmed URLlist_tasks / get_task_status
Find a task and check its status and report-ready time.
freeget_task_report_summary
Whole-report counts and exact tokens held, charged, and returned—without URL rows.
freeget_task_report_page
Read up to 100 selected report rows at a time, with status filters.
freeget_task_report
Full evidence report in one response (can include up to 5,000 rows).
freelist_domains / add_domain / verify_domain
Register a domain, return the exact file an agent should deploy, and verify the required IndexNow key file.
freecreate_topup_link
Get a Stripe checkout link for a token package, for you to open yourself.
freeSupported clients
Claude Code, Claude Desktop, Cursor, VS Code / Copilot, Codex, and Windsurf all support remote MCP servers over Streamable HTTP with a custom header today. Connector support for claude.ai and ChatGPT (OAuth) is coming in a later release. Exact setup snippets for each client, pre-filled with your key, are on the AI agents page once you are signed in.
Notifications
Checker reports are usually ready in about 24 hours. Pay-per-result indexing reports include a seven-day observation window after the last drip-feed day, so use each task’s report_ready_at rather than assuming a fixed deadline. Instead of repeatedly polling, turn on email and/or a webhook per MCP key from AI agents. Either fires once, right after a task created through that key finishes settling. Failed deliveries are retried.
A webhook (https only) receives a POST with this JSON body:
{
"event": "task.report_ready",
"task_id": "...",
"type": "checker" | "indexer" | "backlink",
"engine": "google" | "bing" | "yandex",
"title": "...",
"url_count": 10,
"summary": { "indexed": 8, "not_indexed": 1, "unknown": 1 },
"tokens_charged": 100,
"tokens_returned": 10,
"report_url": "https://rankmeoff.com/app/tasks?task=...",
"created_at": "2026-01-01T00:00:00.000Z"
}Each request carries an X-RankMeOff-Signature header: t=<unix seconds>,v1=<hex HMAC-SHA256>, signed over `${t}.${rawBody}` with the webhook secret shown once when you set the URL. Verify it before trusting the payload:
const crypto = require('node:crypto');
function verify(secret, header, rawBody) {
const parts = Object.fromEntries(
header.split(',').map((p) => p.split('=')),
);
const timestamp = Number(parts.t);
if (!Number.isSafeInteger(timestamp) ||
Math.abs(Date.now() / 1000 - timestamp) > 300 ||
!/^[0-9a-f]{64}$/.test(parts.v1 ?? '')) return false;
const expected = crypto
.createHmac('sha256', secret)
.update(`${parts.t}.${rawBody}`)
.digest('hex');
return crypto.timingSafeEqual(
Buffer.from(expected),
Buffer.from(parts.v1),
);
}A failed delivery retries with backoff and is marked dead after a handful of attempts; the last delivery status is shown per key on the AI agents page, which also has a "Send test" button.
How the agent should behave
The server tells every connecting agent how to choose between search-result checks, URL processing, and backlink checks. Before spending, it must quote with estimate_cost explain the billing mode and total, and confirm with you before spending. max_tokens is a hard total-spend ceiling. The agent must not retry a failed spend automatically or open or pay a top-up link itself. A successful spend returns tokens held or charged and your new balance; a balance under 1,000 tokens (or under 20% of your last purchase) adds a warning your agent should pass along.
For report review, call get_task_report_summary first, then get_task_report_page for selected rows. The full get_task_report tool remains available but may return thousands of rows at once.
