Skip to content
Docs

Audits, tasks and credits

The RankX AI MCP tools that run a Website Audit, work the Tasks board, improve a page section by section, explain changes over time and check credits.

These tools let an assistant turn a finding into a fix. start_site_audit runs a crawl and get_site_audit_issues reads what it found, the task tools turn findings into work, the page-improvement tools rewrite one page with a person deciding every section, get_site_timeline explains what changed and when, and the two credit tools say what any of it costs before you commit.

ToolScopeWhat it does
apply_page_optimisationpublishWrites the sections of a page improvement the user accepted to the live website, and refuses any section that was edited on the site after the suggestion was made rather than overwriting it. Free, and revert_page_optimisation undoes it exactly.
apply_task_fixpublishApplies a task's recommended fix to a connected WordPress site, currently the SEO title and meta description. It spends credits when it generates the suggested fix. Dry run first: it returns the exact before and after, plus a run id you pass back to apply it.
create_taskwriteCreates a task on a Website's Tasks board. Additive only, and it deduplicates: if an open task already tracks the same source, that task is returned rather than a copy.
decide_page_optimisationwriteRecords which sections of a page improvement the user accepted and which they rejected, once they have seen each before and after. That decision is exactly what apply_page_optimisation writes.
get_credit_balancereadCredits available now, credits held by work in flight, the plan allowance, any trial, and grant expiry dates. Free to call, and the right call before proposing anything that spends.
get_credit_usagereadWhere credits went over a period, grouped by action or by Website. Work that failed and was refunded is excluded, so it never reads as spend.
get_page_optimisationreadOne page improvement in full: every section, the proposed rewrite where there is one, the checks it must pass and, 28 days after it is applied, what moved.
get_site_audit_issuesreadThe issues from the most recent completed Website Audit, with severity, category, affected page counts and fix guidance, plus the overall score and crawl statistics.
get_site_audit_statusreadPolls an audit job started by start_site_audit. Once it reports complete, the findings are read with get_site_audit_issues.
get_site_timelinereadWhat RankX AI changed on a Website and when, merged onto one time axis. It states its own blind spots on every response: an empty result means no record, never nothing happened.
list_page_opportunitiesreadThe pages with the most to gain from improvement, each with one reason (losing clicks, losing rank, low click-through rate, an AI citation gap or staleness) and the evidence behind it. An empty list is not a clean bill of health, because each reason says when it could not be checked.
list_tasksreadThe Website's Tasks board, with title, status, category and opportunity score. Dismissed tasks are excluded unless you ask for them.
propose_page_optimisationspendReads a live page, plans the smallest set of changes the evidence supports and rewrites those sections for a person to accept or reject one by one. It spends credits and never changes the website, and a section carrying the page's ranking terms can be protected so it is only added to.
revert_page_optimisationpublishPuts a page back to exactly what it said before an improvement was applied, from the copy RankX AI recorded before writing, and refuses if the page has changed too much since to do that safely.
revert_task_fixpublishUndoes a change apply_task_fix made, restoring the exact values RankX AI recorded before writing. Free, and it dry-runs by default: you see which fields go back to which values before anything is touched. Needs the run id apply_task_fix returned.
start_site_auditspendStarts a Website Audit, either a full crawl or a single-page quick check. Dispatch and poll: it returns a job id immediately and crawls take minutes.

The table above is generated from RankX AI itself rather than written by hand, as at 30 September 2026 (source b27dec96). When the product changes, this page changes with it.

A typical request to an assistant with these tools connected:

Start a site audit on my main website. Tell me what it will cost first, then poll until it finishes and give me the issues by severity.

Running an audit

start_site_audit returns a job id at once while the crawl runs for minutes; poll get_site_audit_status until it reports complete, then read the findings with get_site_audit_issues.

It has two modes: a full crawl, or a quick check of one page. The price scales with the crawl size requested, from the one-page check up to the largest crawl, and a crawl that finishes smaller than requested is charged the cheaper price. The tool's own description carries the current rates.

get_site_audit_issues returns the most recent completed audit, with severity, category, affected page counts and fix guidance, plus the overall score and crawl statistics.

A check that did not run is reported as not assessed, never as passed. RankX AI records which checks each audit ran, so a pass in the result is always a check that ran. See what "a check did not run" means.

The Tasks board

list_tasks reads the board, newest first, with each task's title, status, category and opportunity score. Dismissed tasks are left out unless you ask for them.

create_task adds a task and deduplicates: pass the source that prompted the task, and if an open task already tracks that source, the existing task is returned instead of a copy. That stops an assistant that runs the same analysis twice from filling the board with duplicates.

Applying a task's fix

apply_task_fix applies a task's recommended fix to a connected WordPress site, currently the SEO title and meta description. It changes something outside RankX AI, so it needs the publish scope, and it spends credits when it generates the suggested fix.

It dry-runs by default. The dry run returns the exact before and after and a run id.

Show the diff to the person, and only if they agree call again with the dry run switched off and that run id. Several tasks often point at one page: the diff says how many the change resolves, and they are resolved together for a single charge.

revert_task_fix undoes the change, restoring the exact values RankX AI recorded before writing. It is free, it dry-runs by default, and it needs the run id apply_task_fix returned.

Page improvements

Four tools take one page from "worth improving" to a live change, with a person deciding each section in between.

list_page_opportunities finds the pages. Each comes with one reason (losing clicks, losing rank, a low click-through rate, an AI citation gap or staleness) and the evidence behind it, including the denominator.

propose_page_optimisation writes the proposal. It reads the live page, plans the smallest set of changes the evidence supports and rewrites those sections. It spends credits but never changes the website, and it runs in the background: poll get_page_optimisation until the state is proposed.

decide_page_optimisation records the person's decision, section by section, after they have seen each before and after. Nothing rejected or left undecided is ever written.

apply_page_optimisation writes only what was accepted, for free, because the proposal was already charged for. It reads the page fresh and skips any section edited on the site since the suggestion was made, rather than overwriting that edit.

An empty opportunity list is not a clean bill of health. Every reason has a precondition: a decline needs about 20 clicks in a 28-day window before it is measurable, for instance. The response says which reasons could not be checked and why, and an assistant should pass that on.

A section carrying the page's ranking terms can be protected, so it can only be added to, never rewritten. revert_page_optimisation puts the page back to exactly what it said before, from the copy RankX AI recorded before writing, and refuses if the page has changed too much since to do that safely.

The safeguard here is the decision step rather than a dry run: the proposal is the preview, and only accepted sections are written. Once an improvement has been live for 28 days, get_page_optimisation reports what moved.

The change timeline

get_site_timeline puts every change RankX AI made to the site, every article it published, every audit completed and every task finished onto one time axis, newest first. Use it to explain a movement rather than to find one: fetch the traffic or ranking change first, then ask the timeline what happened around that date.

Every response states what the timeline cannot see. It is a record of what RankX AI did, not a history of the website. An edit made directly in WordPress, a plugin update, a hosting incident and a change at a search engine do not appear in it.

So an empty result means "no record", never "nothing happened", and an assistant should pass that on rather than presenting the timeline as complete. Its counts describe everything that matched, not only the rows returned.

Credits

Both credit tools are free, and calling them first is what turns a proposal into one someone can afford.

get_credit_balance returns credits available now, credits held by work in flight, the plan and its monthly allowance, any trial, and when unspent grants expire. On a credential limited to one client account, it also returns the ceiling set for that client. RankX AI instructs every connected assistant to call it before proposing anything that spends.

get_credit_usage answers "where did my credits go" over a period, grouped by action or by Website. Work that failed is refunded and never reads as spend, and platform-funded onboarding never appears, so the figure is what the account actually spent.

On a credential limited to one client account, grouping by action is refused, because action totals cannot be narrowed to one client. The response points to grouping by Website instead.

Example prompts

List my open tasks with their opportunity scores, and tell me which of them point at the same page.

Apply the SEO title fix for task X. Dry run it first and show me the exact before and after.

Which of my pages have the most to gain from an improvement? Propose one for the top page, then show me every section before and after.

My Search Console clicks dropped around the 14th. What does the site timeline say happened around then, and what can it not see?

What is my credit balance, how much is held by work in flight, and where did my credits go last month by website?

Where to go next

Questions

How does an assistant know what an audit will cost before starting it?

The price is in start_site_audit's own description, resolved from the current rates when your client lists tools. Ask the assistant to call get_credit_balance first, so the price can be weighed against what is available.

Can an assistant undo a fix it applied to my WordPress site?

Yes. revert_task_fix restores the exact SEO title and meta description RankX AI recorded before writing, for free, and revert_page_optimisation puts an improved page back to what it said before.

Is there a limit on how many audits I can run?

No. Site audits are not capped per month on any plan; each crawl is paid for from the credit wallet. See credit costs for the current rates.

Last updated

Cookie settings

Choose which cookies we can use. You can change this at any time from “Cookie settings” in the footer.

Essential

Security, bot protection and remembering your choice. The site needs them to run, and they do not identify you. Always on.

Google Analytics cookies that tell us which pages are read and which links are followed, so we can improve them. Off until you switch it on.

Tells advertisers when their advert led to your visit. Includes the Meta (Facebook) pixel and the LinkedIn Insight Tag, which set cookies on this domain (LinkedIn also on linkedin.com) and can be told if you later start a trial.

More in the cookie policy and the privacy policy.