MCP App Store
by KeenEthics
HarborRank SEO icon

HarborRank SEO MCP Server for Claude and ChatGPT

By HarborRank

Overview

HarborRank lets Claude do real SEO work on live data. Ask things like "What keywords should my plumbing site target?", "Why does competitor.com outrank me?", "Where does my business show on Google Maps across Austin?", "Why did my traffic drop last month?", "Does ChatGPT recommend my brand?" or "Find local businesses I could pitch SEO to." Claude calls HarborRank for the data and answers with numbers you can check. Tools on this server: keyword metrics with volume, difficulty, intent and trends; live Google results with People Also Ask and the AI Overview answer; Google Maps results and a local rank grid that maps a business's position across town as a heatmap; competitor ranking keywords; backlink overviews and backlink strength for up to 1,000 domains; rank tracking with history and competitor positions; site audits compared with the previous audit, plus real-user Core Web Vitals; AI visibility: how often AI answers mention a brand and what ChatGPT, Claude, Gemini and Perplexity answer; keyword clusters mapped to target pages; local lead prospecting with teardowns; read-only Search Console (performance, URL inspection, sitemaps) and Google Analytics 4 (conversions per landing page, AI assistant referrals, channel reports). Claude can publish findings as a shareable report link. A HarborRank account is required. New accounts start with a 7-day free trial: 1,000 research credits, one project, Search Console, Google Analytics and backlink previews. Paid plans add full backlinks, lead research, local rank grids, AI visibility checks, Lighthouse and scheduled rank checks; Pro and Agency add 7x7 grids and up to 10 tracked competitors per tracker. Search Console tools use no credits; research and Analytics tools use plan credits. Data comes from licensed third-party search data and, when connected, the user's own Search Console and Google Analytics.

How to connect

  1. Claude: Open the HarborRank SEO listing in the Claude connectors directory and choose Connect. Claude listing HarborRank SEO exposes 53 tools here.
  2. ChatGPT: Open the HarborRank SEO listing in the ChatGPT app directory and choose Connect. ChatGPT listing HarborRank SEO exposes 52 tools here.

Tools

add_rank_tracker_competitors

ChatGPT
Add competitor domains to a rank tracker so every check also records where they rank for the tracker's keywords, next to the tracked site. Their positions fill in from the next check and show in get_rank_tracker and the app. Use it after competitor research to keep watching the domains that matter. Basic compares up to 3 competitors per tracker; Pro and Agency up to 10. Domains already added are kept. Remove competitors in the app.

ask_ai_models

ChatGPT
Ask ChatGPT, Claude, Gemini and Perplexity the same question with web search on, and get each answer, whether it mentions a brand, the pages it cites (flagging the brand's own), and the searches it ran. Use it to see what AI assistants tell customers about a topic and who they recommend. Paid plans only.

compare_site_audits

ChatGPT
Compare a project's latest completed site audit with the previous audit of the same site: which issues are new, which are still open, and which were fixed, by issue type with sample URLs. An issue counts as fixed only when the latest audit crawled its page again; issues on pages the latest crawl didn't reach are counted as not re-checked. Use it after a round of fixes to show progress, or to catch regressions. Run run_site_audit first if the project has fewer than two completed audits.

create_project

ChatGPT
Create a new project in the user's organization. Provide a name, and optionally a domain and default market (locationCode/languageCode; a languageCode requires a locationCode). Returns the created {id, name, domain, locationCode, languageCode, url}; pass the returned id as projectId to other HarborRank tools. Call list_projects first to avoid creating a duplicate.

create_share_report

ChatGPT
Publishes a read-only report page at a private link anyone with the link can open, without signing in: use it when the user wants to send findings to a client, a boss or a teammate. Write the report from research already done in this conversation. Before publishing, show the user the title and confirm they want a shareable link, and leave out anything they haven't agreed to share (their Search Console or Analytics numbers in particular). Returns the link; reports can be listed with list_share_reports and removed with delete_share_report.

delete_project

ChatGPT
PERMANENTLY deletes a project and everything in it: saved keywords, rank trackers and their history, site audits, leads, brand tracking, and its Search Console connection. Cannot be undone. Only call this after the user has explicitly asked to delete this specific project by name; if they may want the data later, tell them to archive it from the dashboard instead. Pass the project's exact name as confirmName — a mismatch refuses the delete. Returns the deleted {id, name}.

delete_share_report

ChatGPT
Deletes a published report: its link stops working for everyone. Confirm with the user first; this can't be undone.

find_serp_competitors

ChatGPT
Compares domains competing in Google results for a supplied keyword set in a country-level DataForSEO Labs market. Accepts location/language codes; not radius-based local SEO.

get_ai_brand_tracking

ChatGPT
Read the project's tracked AI share of voice over time: the brand, its competitors, and each check's share of voice, oldest first. Set tracking up on the Brand Lookup page; use get_ai_brand_visibility for a one-off look.

get_ai_brand_visibility

ChatGPT
How often ChatGPT and Google's AI answers mention a brand: mentions and AI search volume per platform, share of voice against competitors, the questions that bring the brand up with the sources those answers cite, the pages cited most, and competitors the answers name. Use it to answer 'do AI assistants recommend us?' and to find questions to win. Uses the project's market. Paid plans only.

get_ai_referral_traffic

ChatGPT
Measure real visits the site gets from AI assistants — ChatGPT, Perplexity, Gemini, Copilot, Claude, DeepSeek, Grok and others — from Google Analytics: sessions, engagement, key events (conversions) and revenue per assistant, the share of all traffic AI now drives, and optionally which landing pages they cite. Combines GA4's built-in AI Assistant channel with referrer matching, so it also covers assistants and history the built-in channel misses. Use it to prove AI-search visibility pays off, track its growth with compareTo, and pick pages to optimize for AI answers.

get_analytics_report

ChatGPT
Query the project's connected Google Analytics 4 property: sessions, users, engagement, key events (conversions) and revenue, broken down by channel, source, landing page, page, device, country or date, with optional period-over-period comparison. This is what happens after the click — use it to see which traffic actually converts, explain traffic drops, and back recommendations with business outcomes. Pair with get_search_console_performance for the before-click half, or use get_landing_page_performance to get both joined per page.

get_audit_issues

ChatGPT
Read the prioritized issue report from a completed site audit. Every issue carries a how_to_fix with concrete remediation steps an agent can act on. Omit auditId for the most recent audit.

get_audit_pages

ChatGPT
List crawled pages from a site audit with per-page SEO data (status, title, description, word count, indexability, crawl depth, link counts) and, for pages Lighthouse checked, mobile and desktop scores (performance, accessibility, best practices, SEO) and LCP, CLS, INP and TTFB. Omit auditId for the most recent audit.

get_audit_status

ChatGPT
Check the progress of a site audit (phase, pages crawled, Lighthouse progress). Omit auditId for the most recent audit.

get_core_web_vitals

ChatGPT
Real-user Core Web Vitals from the Chrome UX Report: the 28-day p75 for LCP, INP, CLS and TTFB with the share of good, needs-improvement and poor visits, plus about 40 weeks of weekly p75 history. Reads the whole site of the project's domain by default, or one page when url is given (any public site works, so it can check a competitor too). Phone data unless formFactor says otherwise. A no_data status means Chrome hasn't collected enough real-user visits for that site or page.

get_domain_keyword_suggestions

ChatGPT
Returns the organic keywords a domain ranks for, including position and available metrics. Use after get_domain_overview when you want the detailed keyword opportunity list for a competitor or reference domain. Cached for 12 hours.

get_domain_overview

ChatGPT
Returns a high-level view of a domain's organic footprint: estimated organic traffic, organic keyword count, backlinks, and referring domains. Use this first for domain research; for the detailed ranked-keyword list, call get_domain_keyword_suggestions next. Cached for 12 hours per domain.

get_domain_ranks

ChatGPT
Get the backlink rank (0-100) of up to 1,000 domains in one call. Use it to compare the strength of the sites in a SERP, a competitor list, or a list of directories and link prospects. A null rank means there is no backlink data for the domain yet (usually a new or tiny site). For one domain's full backlink profile, use get_backlinks_overview.

get_google_business_questions

ChatGPT
Fetches Google Business Profile questions and answers for one business keyword near a coordinate. Run this only when Q&A evidence is needed.

get_keyword_metrics

ChatGPT
Hydrate up to 700 known keywords with search volume, keyword difficulty (KD), search intent, CPC, competition, and monthly trends in a single call. Use it to score candidate or known keywords — including Search Console striking-distance queries — by real demand and ranking difficulty. For countries served from Google Ads data (e.g. Iceland), KD and intent are null.

get_landing_page_performance

ChatGPT
The full SEO funnel per page in one call: Google Search Console clicks, impressions and position joined with Google Analytics organic sessions, engagement, key events (conversions) and revenue for each landing page. Answers 'which pages bring customers, not just clicks?', finds pages that rank but don't convert (fix the page) and pages that convert but barely rank (worth pushing), and flags pages earning Google clicks that Analytics never records (broken tracking). Best starting point for SEO prioritization, content audits and client reporting. Works with Analytics alone if Search Console isn't connected.

get_lead_teardown

ChatGPT
Returns the Markdown teardown research_lead generated for a lead: pack positions from three points, the searches that bring jobs, the top-three profile comparison, website footprint and audit findings, and the fixes.

get_local_grid

ChatGPT
Without gridId, lists the project's local rank grids. With gridId, returns its latest scans (newest first), each with the grid of Maps positions and its top-3 share and average position, to show change over time. Run new scans with run_local_grid.

get_local_serp_results

ChatGPT
Fetches one Google Maps or Local Finder SERP near a coordinate. Returns one row per listing (rank, title, domain, URL, category, rating, reviews, phone, address, claimed status, place_id, cid, coordinates); match a target business by place_id, cid, domain or title.

get_rank_history

ChatGPT
Read-only position history for a rank tracker's keywords over its latest completed checks (up to 26), newest first, for one device. Each keyword row lists its position per check. A null position (— in text) means the domain was not found in that check's results; checked: false (not checked in text) means that check got no result for the keyword, so it says nothing about the position. Checks that only re-ran some keywords are left out. Use get_rank_tracker first for the trackerId and trackingKeywordId values.

get_rank_tracker

ChatGPT
Read-only access to rank tracker configs and their latest results. With trackerId, returns config + latest snapshot per keyword. Without it, lists all trackers in the project. To trigger a new check, use the dashboard.

get_ranked_keywords

ChatGPT
Returns market-specific keyword, rank, search volume, keyword difficulty (KD), CPC, intent, estimated traffic and ranking URL rows for a domain or page. Accepts country-level DataForSEO Labs location/language codes. Use this for strategy evidence; use get_domain_overview for aggregate domain footprint.

get_search_console_performance

ChatGPT
Query the connected Search Console property's Search Analytics: clicks, impressions, CTR, and average position by query/page/country/device/date. First-party data — use it for what already ranks, near-ranking queries, and pages with real demand. ctr is a 0-1 fraction; position is a 1-based average; dates are Pacific Time; the last ~3 days may be incomplete. Read-only.

get_search_console_sitemaps

ChatGPT
List the sitemaps submitted in Google Search Console for the project's connected property: when Google last read each one, whether it's still pending, its error and warning counts, and how many URLs it submits. Use it to check that a sitemap is submitted and being read, or to find a sitemap with errors. Read-only: submit or remove sitemaps in Search Console itself.

get_serp_results

ChatGPT
Fetch live Google organic search results for 1-10 keywords. Use this to inspect who ranks for a query, verify competitors, compare SERPs across keywords, or gather source URLs before content planning. Does not save results to HarborRank. Per-keyword errors don't fail the batch.

inspect_urls

ChatGPT
Run Google Search Console's URL Inspection on up to 10 URLs of the connected property: index/coverage state, last crawl time, Google-selected vs declared canonical, and mobile/rich-results verdicts. Use it to answer 'is this page indexed? why not?'. Per-URL failures are reported inline. Read-only.

list_business_categories

ChatGPT
Lists the Google Business category taxonomy used by prospect_leads' categories filter, sorted by listing count. Use to find the right category slugs for a niche.

list_leads

ChatGPT
Lists the project's saved prospecting leads with their track and outreach status.

list_projects

ChatGPT
Lists all projects in the user's organization. Use this whenever you need a projectId for another HarborRank tool. Returns an array of {id, name, domain, locationCode, languageCode}; pass the id value as projectId. locationCode/languageCode are the project's default market — tools fall back to them when a call omits location/language args.

list_saved_keywords

ChatGPT
Lists keywords saved to a project (with cached metrics like search volume, difficulty, CPC, and tags if available). Use tag filters when the user asks for a saved segment; multiple tags match ANY tag.

list_share_reports

ChatGPT
Lists the reports this workspace has published with create_share_report, newest first, with each link, its view count and its id.

prospect_leads

ChatGPT
Searches Google Business listings for a niche and saves new businesses to the project's lead list (deduped by place and domain). Two modes: city (locationCode — a Google Maps search for the niche in that city) or coordinate (latitude/longitude/radiusKm). Stores each listing's coordinates and profile depth (photos, categories, 24h hours) so research_lead can check pack positions around the business. Use list_leads to read the list back.

research_keywords

ChatGPT
Research keyword data (search volume, difficulty, CPC, related ideas) for 1-5 seed keywords in one call. In countries served from Google Ads data, difficulty and intent are unavailable. Returns per-seed results — a single bad seed won't fail the batch.

research_lead

ChatGPT
Runs HarborRank's in-product research on a saved lead and stores the evidence: money keywords with volume, the lead's Google Maps position and who holds #1, the primary keyword checked from three points around the business, the top three competitors with profile depth (photos, categories, 24h hours, Q&A, distance), the lead's organic footprint, contact discovery, an optional AI Overview check, and a quick site audit. Then writes the Markdown teardown that get_lead_teardown returns. On hosted HarborRank this requires a paid plan.

run_local_grid

ChatGPT
Check where a business shows up in Google Maps for one keyword from a square of points around it (3x3, 5x5 or 7x7), the way a local SEO agency shows a client where in town they appear. Returns the grid of positions (north at the top), the share of points in the top 3, and the average position, and saves the scan to the project so it can be compared later. Pass gridId to re-run a saved grid, or the business's name and coordinates (and place_id when known) to create one. Paid plans; 7x7 grids need Pro or Agency. Takes up to a minute for a 7x7 grid.

run_site_audit

ChatGPT
Start a site audit with HarborRank's own crawler (no third-party API): crawls the site at the given URL (robots.txt-aware, same-origin), checks every page for SEO issues (broken links, duplicate/missing titles and descriptions, redirect chains, orphan pages, canonical problems, thin content, and more), and optionally runs Lighthouse on a sample of pages. Runs in the background — poll get_audit_status, then read get_audit_issues. If the site blocks our crawler, pages are honestly flagged as blocked rather than misreported.

save_keywords

ChatGPT
Save keywords to a project's saved-keywords list. Idempotent: re-saving an existing keyword is a no-op. If tags are provided, missing tags may be created. By default tags are appended; set tagMode=replace to remove existing tags from these saved keywords before applying the provided tags, which is useful for reorganizing keywords into page/topic clusters. Ask the user for confirmation before applying or replacing tags broadly.

search_local_businesses

ChatGPT
Searches local business listings near a coordinate. Use this to find local business candidates or nearby competitors; it does not run Maps rank checks or Q&A.

set_cluster_target_page

ChatGPT
Assign the page a keyword cluster should rank with. A cluster is a saved-keyword tag: save the cluster's keywords with save_keywords under one tag, then call this with that tag and the page (existing or planned). The mapping shows on the tag in Saved Keywords, so the keyword map stays with the project. It replaces the page set before, if any; pass targetUrl null to clear it.

set_lead_competitors

ChatGPT
Stores the named competitors shown side-by-side in a lead's report. Replaces the lead's existing competitor list.

set_lead_serp_checks

ChatGPT
Stores real search-ranking evidence for a lead's report: per keyword, the search volume, the lead's actual position, and the top-ranking business. Replaces the lead's existing checks.

set_lead_top_issues

ChatGPT
Stores a lead's top audit findings in plain English — the raw material for the teaser email and report. Replaces the lead's existing list.

update_lead

ChatGPT
Updates a saved lead's track, outreach status, owner name, contact email, or notes. Use after audits (status='audited') or when outreach state changes.

whoami

ChatGPT
Returns the authenticated user, organization, server mode, token scopes, plan, and current credit balance, with a warning once 75% of the monthly credits are used. Use this first to confirm connection context before choosing a project or running research tools, and again to confirm a plan change.

add_rank_tracker_competitors

Claude

ask_ai_models

Claude

compare_site_audits

Claude

create_project

Claude

create_share_report

Claude

delete_project

Claude

delete_share_report

Claude

find_serp_competitors

Claude

get_ai_brand_tracking

Claude

get_ai_brand_visibility

Claude

get_ai_referral_traffic

Claude

get_analytics_report

Claude

get_audit_issues

Claude

get_audit_pages

Claude

get_audit_status

Claude

get_core_web_vitals

Claude

get_domain_keyword_suggestions

Claude

get_domain_overview

Claude

get_domain_ranks

Claude

get_google_business_questions

Claude

get_keyword_metrics

Claude

get_landing_page_performance

Claude

get_lead_teardown

Claude

get_local_grid

Claude

get_local_serp_results

Claude

get_rank_history

Claude

get_rank_tracker

Claude

get_ranked_keywords

Claude

get_search_console_performance

Claude

get_search_console_sitemaps

Claude

get_serp_results

Claude

inspect_urls

Claude

list_business_categories

Claude

list_leads

Claude

list_projects

Claude

list_saved_keywords

Claude

list_share_reports

Claude

prospect_leads

Claude

research_keywords

Claude

research_lead

Claude

run_local_grid

Claude

run_site_audit

Claude

save_keywords

Claude

search_local_businesses

Claude

set_cluster_target_page

Claude

set_lead_competitors

Claude

set_lead_serp_checks

Claude

set_lead_top_issues

Claude

update_lead

Claude

whoami

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/harborrank"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/harborrank)