Skip to main content
The MCP server is most valuable for questions that span several parts of the platform — the ones that would otherwise mean opening four pages and reconciling them by hand. These are patterns that work.

Weekly review

Look at the project for example.com. Summarize what changed this week: ranking movement, new and lost backlinks, and anything from the latest audit. Lead with what needs attention.
The agent chains get_ranking_changes, get_new_lost_backlinks, and get_audit_summary, then writes the summary. Faster than three pages, and it does the correlation for you.

Triage an audit for developers

Read the most recent audit for this project. Group the issues by severity, and for each group say what a developer would actually have to change. Put anything that’s a template-wide fix first.
Uses list_audits, get_audit_summary, and get_audit_issues. The value is the last sentence — sitewide patterns are one fix each and move the score far more than one-off issues.
Run a backlink gap for this project against competitor-a.com, competitor-b.com, and competitor-c.com. Rank the results by how many of the three link to them and by domain authority, and tell me which ten to approach first.
get_backlink_gap compares your project’s site against up to four competitors and returns the raw comparison; the agent does the ranking. It waits up to two minutes; if the analysis is still running, the agent collects it with get_backlink_gap_result rather than calling get_backlink_gap again, which would buy a second one. Domains linking to all three competitors are the strongest targets — your absence is conspicuous rather than a matter of taste.

Plan content for a topic

We want to rank for “rank tracking for agencies”. Research the keyword and related terms, check who’s currently cited in AI answers for it, then write a content brief.
Chains research_keyword, get_keyword_suggestions, and get_ai_top_competitors, then the agent writes the brief itself from what they returned — the search intent and difficulty from the research, the related terms as headings and questions to cover, and the domains AI answers already cite as the pages to beat. Surnex doesn’t generate the brief; the model does, from your data, in one conversation.

Audit your AI visibility

Run a citation gap for this project against our competitors on our top 20 commercial keywords. For every gap, tell me which sources were cited instead and whether they mention us at all.
get_citation_gap plus get_chatgpt_visibility on the gaps. The second half is the useful part: if a comparison site is cited and doesn’t list you, the fix is getting listed, not editing your own page.

Set up local tracking

Find the Google Business listing for Austin Plumbery in Austin, TX, add it as a location with a 5×5 grid 1 km apart, and track “plumber near me” and “emergency plumber” there. When the first check lands, tell me where on the map we’re outside the top 3 and who ranks above us there.
Chains search_local_listings, add_local_location, add_local_keywords and get_local_grid. The first check starts as soon as the keywords are added and takes a few minutes. The last step is the useful one: the grid’s top 3 at each weak point names the competitors to study.

Cross-referencing

The strongest prompts join data that lives in different places:
Which keywords did we lose top-10 positions on this month, and do any of the pages that dropped have audit issues?
Compare our tracked keyword positions against our AI Overview citation rate. Are we losing traffic on keywords where we still rank well?
Which of our top pages by traffic have the worst web vitals?
None of these is a page in the dashboard. That’s the point of the integration.

Prompting well

Name the project. “The project for example.com” saves the agent guessing between several. State the market. Adding keywords and prompts, the AI searches and the listing search start on the project’s own market; research, trends and domain lookups default to United States and English. If you target another market, say so for those. Ask for a conclusion, not a dump. “Tell me the ten to approach first” produces something usable; “get the backlink gap” produces a table you still have to read. Bound the scope. “Top 20 commercial keywords” rather than “our keywords” keeps quota consumption predictable.

Being careful

Turn on tool approval if your client supports it. The agent can call delete_project, which destroys all of a project’s history irreversibly. Watch quota. Research, audits, backlink refreshes, AI lookups, and domain lookups (get_domain_overview, get_domain_top_keywords, get_domain_top_pages, get_domain_competitors, get_tech_stack) all draw on your monthly plan allowances. Creating a project does too — its first run spends at least five research lookups, one AI brand audit, and up to 101 site audit pages. An agent asked to audit every project will spend your monthly site audit pages doing exactly that — audits cost the pages they crawl. Verify writes. Before asking an agent to add fifty keywords, have it call get_usage_summary to confirm you have room under your tracked keyword limit — hitting it mid-run leaves a partial result.