RankCLI

io.github.integrallis由 GitHub 帳號 integrallis 發布v0.0.31更新於 Nov 4, 2026

面向AI助理的免費本機SEO + GEO審計——無需註冊，資料不會離開你的裝置。

AI 翻譯由 AI 模型根據下方的原文描述翻譯，可能有誤。

原文描述

Free, local SEO + GEO audits for AI assistants - no signup, nothing leaves your machine.

發布方自己的服務：Rank Fast

已驗證STDIO僅桌面網頁搜尋與抓取開發者工具

服務詳細資訊

識別碼: io.github.integrallis/rankcli-mcp-server
傳輸: STDIO
執行環境: Desktop only
信任: Verified
發布於: Sep 16, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此條目所屬的 GitHub 帳號 integrallis。這並不表明該帳號就是產品方。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.integrallis%2Frankcli-mcp-server.svg)](https://sourceweft.com/mcp/io.github.integrallis%2Frankcli-mcp-server?utm_source=readme&utm_medium=badge)

概覽

RankCLI 的本機 MCP 服務；無需登入；STDIO；15 個工具。

暫無 AI 概覽：以下資訊來自註冊中心條目和服務本身。

安裝

在 SourceWeft 中

開啟儀表板中的 RankCLI，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照儲存庫中的啟動說明。

README

@rankcli/mcp-server

Free, local SEO + GEO (AI-search-citation) analysis as an MCP tool. No signup, no API key, nothing sent to RankCLI's servers — it runs entirely inside your MCP host (Claude Code, Claude Desktop, Cursor, etc.) against HTML you already have or that your host fetches for you. The one exception is rankcli_connect, an explicit opt-in tool that links this server to a RankCLI account.

Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

json

{  "mcpServers": {    "rankcli": {      "command": "npx",      "args": ["@rankcli/mcp-server"]    }  }}

{  "mcpServers": {    "rankcli": {      "command": "npx",      "args": ["@rankcli/mcp-server"]    }  }}

Prefer not to run anything locally? The same tools are available at a free hosted HTTP endpoint, no npx and no signup:

Available Tools

Tool	Description
`seo_analyze`	Full SEO analysis: GEO, Core Web Vitals, structured data, security headers, mobile, images, internal linking
`seo_geo_check`	AI search visibility (GEO) — crawler access, LLM content signals, citation readiness
`seo_robots_ai`	Which AI crawlers (GPTBot, ClaudeBot, PerplexityBot, etc.) your robots.txt allows or blocks
`seo_generate_robots`	Generate an AI-crawler-friendly robots.txt
`seo_core_web_vitals`	Estimate LCP, CLS, INP, TTFB from HTML
`seo_structured_data`	Validate JSON-LD / Schema.org markup
`seo_generate_schema`	Generate a JSON-LD template for a page type
`seo_security_headers`	Grade HTTPS, HSTS, CSP, and related headers
`seo_generate_security_headers`	Generate recommended security header config
`seo_images`	Alt text, dimensions, formats, lazy loading
`seo_internal_links`	Anchor text quality, orphan-page risk
`seo_mobile`	Viewport, touch targets, PWA readiness
`seo_ai_crawlers`	Reference list of known AI crawler user agents
`rankcli_connect`	Link this server to a RankCLI account for GitHub auto-fix PRs, scheduled monitoring, and a dashboard with audit history. Opens a browser tab to approve; the only tool here that contacts rankcli.dev
`rankcli_disconnect`	Unlink this server from your RankCLI account (local only — doesn't touch the account itself)

Connecting your account

Ask Claude to "connect my RankCLI account," or call rankcli_connect directly. It opens rankcli.dev in your browser to approve (or asks for permission first, on MCP hosts that support that inline) - once approved, this server and the rankcli CLI on the same machine both use the connection, with nothing further to configure. It works the same on the free plan: connect a BYOK AI provider key at rankcli.dev/account?tab=ai-provider and auto-fix PRs run on your own key at no cost, including several providers with genuinely free tiers.

Example

Just ask Claude:

"Run an SEO audit on https://example.com"

Your MCP host fetches the page and Claude calls these tools directly — nothing round-trips through RankCLI.

Want more?

This local server works from HTML/robots.txt you or your MCP host supply. For URL-only tools that fetch and crawl for you (seo_audit, seo_geo_check, seo_robots_check, seo_compare), plus the newer Cloudflare AI-crawler-gating compliance check, CI/CD scheduling, and auto-fix PRs, see the hosted endpoint and paid tiers:

json

{  "mcpServers": {    "rankcli-hosted": {      "url": "https://mcp.rankcli.dev/mcp",      "headers": {        "Authorization": "Bearer YOUR_API_KEY"      }    }  }}

{  "mcpServers": {    "rankcli-hosted": {      "url": "https://mcp.rankcli.dev/mcp",      "headers": {        "Authorization": "Bearer YOUR_API_KEY"      }    }  }}

Get a free API key at rankcli.dev/dashboard.

工具

seo_analyze

Run comprehensive SEO analysis on a webpage. Returns scores and issues for: - GEO (AI Search Optimization) - Is the site visible to ChatGPT, Perplexity, Claude? - Core Web Vitals (LCP, CLS, INP) - Performance estimates - Structured Data - Schema.org validation - Security Headers - HTTPS, HSTS, CSP - Mobile SEO - Responsive design, touch targets - Images - Alt text, formats, dimensions - Internal Linking - Anchor text, orphan detection Use this for a complete SEO audit.

輸入參數url必填htmlrobotsTxt

seo_geo_check

Check if a website is optimized for AI search engines (GEO - Generative Engine Optimization). Analyzes: - AI crawler access by class (search, AI search, user-triggered, training crawlers) - robots.txt rules for AI crawlers - JS rendering requirements (can AI crawlers see content?) - Content structure for LLM consumption - Citation readiness (trust signals) - FAQ/entity extraction capability Critical for visibility in ChatGPT, Perplexity, Claude, and Gemini responses.

輸入參數url必填htmlrobotsTxt

seo_robots_ai

Analyze robots.txt for AI crawler access by class: search crawlers (Googlebot, bingbot), AI search crawlers (OAI-SearchBot, Claude-SearchBot, PerplexityBot), user-triggered fetchers (ChatGPT-User, Claude-User, Perplexity-User) and training crawlers (GPTBot, ClaudeBot, CCBot, Google-Extended), with what blocking each class costs.

輸入參數robotsTxt必填

seo_generate_robots

Generate a robots.txt that allows every crawler class, with one group per class (AI search, user-triggered, training) so a site can disallow training alone without losing search or answer visibility.

輸入參數siteUrl必填

seo_core_web_vitals

Estimate Core Web Vitals (LCP, CLS, INP, TTFB) from HTML analysis. Identifies issues like: - Render-blocking resources - Images without dimensions - Large JavaScript bundles - Missing preload hints

輸入參數url必填html必填

seo_structured_data

Validate JSON-LD structured data (Schema.org). Checks for: - Required properties per schema type - Article, Product, FAQ, HowTo, LocalBusiness schemas - Rich result eligibility - Common mistakes

輸入參數url必填html必填

seo_generate_schema

Generate JSON-LD structured data template for a page type (article, product, faq, local-business, website).

輸入參數siteUrl必填pageType必填siteName必填authorNameorganizationName

seo_security_headers

Analyze security headers (HTTPS, HSTS, CSP, X-Frame-Options, etc.). Returns a security grade A+ through F.

輸入參數url必填headers必填

seo_generate_security_headers

Generate recommended security headers configuration for a site.

輸入參數siteUrl必填

seo_images

Analyze images for SEO and performance. Checks alt text, dimensions, formats (WebP/AVIF), lazy loading, and responsive images.

輸入參數url必填html必填

seo_internal_links

Analyze internal linking structure. Checks anchor text quality, orphan page risk, link distribution, and suggests linking opportunities.

輸入參數url必填html必填

seo_mobile

Analyze mobile SEO. Checks viewport, touch targets, font sizes, content width, PWA readiness.

輸入參數url必填html必填

seo_ai_crawlers

List the known crawlers by what they are for (search, AI search, user-triggered, training), who runs each, and what blocking it costs.

無需輸入參數。

rankcli_connect

Link this AI assistant to a RankCLI account (rankcli.dev). This is the only tool in this server that contacts rankcli.dev, and only when you call it - every other tool runs fully locally. Connecting unlocks GitHub auto-fix PRs, scheduled monitoring, and a dashboard with history across audits; it does not change how the other tools work. Opens a browser tab for the user to approve (or reuses an existing session if already logged in). Safe to call anytime - if already connected, it just reports who's connected.

無需輸入參數。