HarborRank

com.harborrankPublished by harborrank.comOfficial publisherv1.2.0Updated Oct 31, 2026

SEO for AI agents: keywords, SERPs, backlinks, rank tracking, audits, Search Console, Analytics

Overview

AI-generated overview

Remote HarborRank server that gives an assistant live SEO data: keywords, Google SERPs, backlinks, rank tracking, site audits, Search Console and Analytics.

What you can do
  • Read Search Console, Analytics, landing-page and AI-referral performance for connected properties
  • Research keywords, fetch metrics and domain suggestions, and save or list keyword sets
  • Pull live Google SERPs, local results, SERP competitors and Google Business questions
  • Inspect competitors' ranked keywords and backlink profiles
  • Run site audits and review status, issues and pages
  • Track rankings, create or delete shareable reports, and manage projects and local leads
When to use it
Useful for SEO work that needs live numbers rather than guesswork: keyword shortlists, competitor and backlink analysis, indexing and audit checks, client reports, and local lead prospecting for agencies. The README also ships eighteen companion SEO skills for agents that read SKILL.md files.
Requirements
A HarborRank account signed in through OAuth 2.0 (dynamic client registration) against the remote Streamable HTTP endpoint; no API keys or environment variables are declared. A card is added at signup. An agent that can connect to a remote HTTP MCP server, such as Claude, ChatGPT, Cursor, Codex or Gemini CLI. Connecting Google Search Console and Analytics properties is optional.
Before you install
Paid service: signup requires a card, a 7-day trial with 1,000 credits is followed by a $29/month Basic plan unless cancelled from Billing, and backlinks, lead research and Lighthouse checks need a paid plan. Research and Analytics tools consume plan credits. Tool calls send keywords, domains, URLs and project ids to HarborRank, which fetches data from licensed third-party providers and, if connected, read-only Google Search Console and Analytics data. Some tools write or delete…

Installation

In SourceWeft

  1. Open HarborRank in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.harborrank%2Fharborrank/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "harborrank": {
      "type": "http",
      "url": "https://app.harborrank.com/mcp"
    }
  }
}

README

Claude SEO skills and SEO MCP server (HarborRank)

[smithery badge] [Indexed on TensorBlock MCP Index] [HarborRank MCP server on Glama]

Eighteen free, MIT-licensed Claude SEO skills, plus the HarborRank SEO MCP server that gives them live keyword, SERP, backlink and Google Search Console data. The MCP server works in Claude, ChatGPT, Cursor, Codex and Gemini CLI, and the skills work in any agent that reads SKILL.md files. Every skill works on its own from web evidence and your files, and gets live numbers when HarborRank is connected.

Contributions welcome. Found a way to improve a skill or have a new SEO workflow to add? See CONTRIBUTING.md and open a PR.

Each skill is one slash command. With HarborRank connected, the skills pull live data through the HarborRank MCP server: keyword metrics, SERPs, ranked keywords, backlinks, rank tracking, Google Search Console, and Google Analytics.

Install in Claude (web, desktop, Cowork)

  1. Install HarborRank SEO from the plugin directory, or add the HarborRank connector (Customize, then Connectors).
  2. Choose Connect and sign in to HarborRank with Google or email to start your 7-day free trial.
  3. Back in Claude, ask for something real, for example "Find 20 low-difficulty keywords for mysite.com and save the best ones to my project" or "Which of my pages sit at positions 8 to 20 in Search Console?"

If you ask before connecting, Claude says HarborRank isn't connected, gives these steps, and picks the task back up once you say "connected".

Install as a Claude Code plugin

One install adds the HarborRank MCP server and all eighteen skills. Inside Claude Code:

/plugin marketplace add winsley-jeune/harborrank-skills/plugin install harborrank@harborrank

Then run /mcp, pick harborrank, and sign in (setup guide). The first MCP call opens the HarborRank login in your browser. Installed this way the skills run as /harborrank:<name>, for example /harborrank:keyword-research.

Install in Cursor

Add the MCP server in ~/.cursor/mcp.json:

json
{ "mcpServers": { "harborrank": { "url": "https://app.harborrank.com/mcp" } } }

Cursor opens the HarborRank login the first time it connects. This repository is also a Cursor plugin (.cursor-plugin/) that adds the server and the eighteen skills in one install.

Install in ChatGPT

Add HarborRank from ChatGPT's plugin directory and sign in when ChatGPT asks. It connects the same MCP server; the skills in this repository are for agents that read SKILL.md files.

Install as a Gemini CLI extension

gemini extensions install https://github.com/winsley-jeune/harborrank-skills

Then run /mcp auth harborrank in Gemini CLI to sign in. The extension adds the MCP server and the eighteen skills.

Requirements

  • A HarborRank account. Start free: new accounts get a 7-day free trial with 1,000 research credits, one project, Search Console, and Google Analytics. You add a card at signup; Basic ($29/month, 15,000 credits a month) starts when the trial ends unless you cancel from Billing first. Backlinks, lead research, and Lighthouse checks need a paid plan, and you can email [email protected] within 7 days of the first charge for a full refund.
  • Claude Code, Cursor or Gemini CLI (or another agent that reads SKILL.md files and can connect to a remote HTTP MCP server).

What the MCP server can do

One remote server, https://app.harborrank.com/mcp (Streamable HTTP, OAuth 2.0 with dynamic client registration), with 41 tools:

AreaTools
Your own data (read-only)get_search_console_performance, inspect_urls, get_analytics_report, get_landing_page_performance, get_ai_referral_traffic
Keyword researchresearch_keywords, get_keyword_metrics, get_domain_keyword_suggestions, save_keywords, list_saved_keywords
Live Google resultsget_serp_results, find_serp_competitors, get_local_serp_results, search_local_businesses, get_google_business_questions
Competitors and linksget_domain_overview, get_ranked_keywords, get_backlinks_overview, get_backlinks_profile
Site auditsrun_site_audit, get_audit_status, get_audit_issues, get_audit_pages
Rank tracking and reportsget_rank_tracker, create_share_report, list_share_reports, delete_share_report
Local leads for agencieslist_business_categories, prospect_leads, research_lead, get_lead_teardown, list_leads, update_lead, set_lead_competitors, set_lead_serp_checks, set_lead_top_issues
Account and projectswhoami, list_projects, create_project, delete_project, get_upgrade_link

Check that it works

After connecting, ask your agent:

  1. "Which HarborRank account am I connected to?" It calls whoami and answers with the account and the credits left.
  2. "List my HarborRank projects." It calls list_projects.
  3. "Show the live Google results for 'best running shoes'." It calls get_serp_results and returns the top results.

If a call answers that the account needs a plan or more credits, the text of the reply says what to do next.

Example prompts

  • "Research keywords for a Plymouth, MA marine electrician: shortlist ten with volume, difficulty and intent, and save the good ones to my project."
  • "Who ranks for my saved keywords, and where are the openings a small site could take?"
  • "Which of my pages bring in leads from Google, and how much of my traffic now comes from ChatGPT and other AI assistants?"
  • "Is /pricing indexed? If not, why not, and which of my pages are sitting at positions 8 to 20?"

What the plugin runs, sends and fetches

Install the skill files only

For Codex or any agent that reads SKILL.md files, or if you already added the MCP server by hand:

bash
npx skills add winsley-jeune/harborrank-skills

Install everything for Claude Code only:

bash
npx skills add winsley-jeune/harborrank-skills --skill '*' --agent claude-code

Or copy the folders under skills/ into ~/.claude/skills/ (Claude Code) or ~/.codex/skills/ (Codex).

If you install the files only, connect HarborRank MCP first. The skill files are instructions, not data: without the MCP connection your agent only has what it can see on its own.

Skills

CommandWhat it does
/seo-project-setupCreate a local workspace with goals, competitors, exports, and preferences that later sessions reuse.
/seo-contextWrite the one-page context file (site, market, audience, competitors, goals) that every other skill reads first.
/seo-coachPick the next workflow when you are new to SEO or unsure what to run first.
/keyword-researchTurn seed topics into a prioritized keyword shortlist with volume, difficulty, intent, and SERP caveats.
/keyword-clusteringGroup a keyword list by intent, map clusters to pages, and flag cannibalization.
/competitive-landscapeMap who wins a market, why, and where the openings are.
/competitor-analysisStudy one competitor's keywords, pages, and backlinks and turn it into takeaways.
/seo-auditCrawl the site for technical issues, check indexing, and find why traffic dropped, with fixes ranked by impact (the crawl and Search Console checks use no credits).
/content-briefTurn one target keyword into a brief built from the live SERP: questions to answer, what to add that page one lacks, outline, links, schema and title.
/local-seoCheck where a local business ranks in Google Maps across its service area, compare it with the businesses above it, and get a local action plan.
/client-seo-reportWrite a monthly SEO report for a client or boss from Search Console, Analytics and rank tracking, and publish it as a shareable link.
/keyword-cannibalizationFind queries where two of your pages compete in Search Console, fix only the splits that cost traffic, and check Google's chosen canonical.
/google-business-profileAudit a Google Business Profile against the Maps leaders: categories, services, description, reviews, Q&A, NAP and landing page, with ready-to-paste text.
/schema-markupFind the structured data each page type has, write JSON-LD that matches the visible content, and validate it.
/ai-search-visibilitySee how often AI assistants send visits and cite the site, which sources they cite instead, and what to change to get cited.
/seo-proposalTurn a prospect's teardown into an SEO proposal: current state with numbers, opportunity ranges, a 90-day plan, and a cover email.
/link-prospectingFind qualified link prospects and the angle that makes each one relevant.
/lead-teardownProspect local businesses in a trade and city, research each one, and get a one-page teardown to send as the pitch (research needs a paid plan).

Docs for every skill: harborrank.com/docs/skills. What the skills are for and how they compare: Claude SEO skills built on live search data.

License

MIT. See LICENSE for the copyright holders.

Source: README.md at commit 371d9c7

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

3
  1. v1.2.0LatestOct 17, 2026
  2. v1.1.0Oct 9, 2026
  3. v1.0.0Sep 27, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts