GetBotRank Free AI Search Tools

io.github.lazycipher由 GitHub 账号 lazycipher 发布v1.0.0更新于 Nov 8, 2026

Free, no-auth tools for AI search visibility: robots.txt, schema, rendering, sitemap, PageSpeed.

发布方自己的服务：Rank Fast

已验证Streamable HTTP可网页运行网页搜索与抓取开发者工具

服务详情

标识符: io.github.lazycipher/getbotrank-free-tools
传输: Streamable HTTP
运行时: Web executable
信任: Verified
发布于: Nov 8, 2026

安全提示

MCP 服务会接收对话中的工具调用请求，并可能执行外部操作。启用前请先了解该服务能做什么，并只授予它所需的权限。

注册中心已验证此条目所属的 GitHub 账号 lazycipher。这并不表明该账号就是产品方。

SourceWeft 的检查只涵盖条目是否完整、端点是否响应；不审查服务器的代码，也不审查其工具的行为。

在 README 中添加徽章

向读者展示该 MCP 服务已收录于 SourceWeft，徽章链接到本页。

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

概览

AI 生成的概览

免费、无需认证的远程 MCP 服务器，用于检查网站对 AI 搜索引擎和爬虫的可抓取性与可引用性。

可以做什么: 测试 robots.txt 规则与 AI 爬虫访问权限，并以爬虫视角查看页面
校验结构化数据、站点地图与 hreflang，并生成 llms.txt
检查元数据、社交预览、重定向链与 Open Graph 卡片数据
评估段落可引用性、页面速度与 Common Crawl 收录情况，并查询品牌实体
运行综合 AI 就绪度审计，给出 0 到 100 分
验证 IndexNow 密钥，并可选提交最多 100 个网址
适用场景: 适合让助手审计网站的 AI 搜索就绪度、诊断 AI 爬虫为何被拦截或抓不到内容，或在不切换多个工具的情况下检查结构化数据、站点地图和元数据。
运行要求: 一个远程 Streamable HTTP 端点，无需 API 密钥或账号。仅支持 stdio 的客户端需通过 npx 使用 mcp-remote 之类的桥接。需要能访问该端点及被检查的网址；页面速度结果来自 Google PageSpeed Insights。

安装前请注意

当 action 设为 submit 时，submit_indexnow 会在密钥文件验证通过后向 api.indexnow.org 提交最多 100 个网址。对你提供的网址的请求由第三方服务以 GetBotRankBot 身份抓取，结果可能缓存 24 小时。调用按 IP 限流（每 15 分钟 20 次）。

安装

在 SourceWeft 中

打开控制台中的 GetBotRank Free AI Search Tools，将其添加到工作区。
为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.lazycipher%2Fgetbotrank-free-tools/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "getbotrank-free-ai-search-tools": {
      "type": "http",
      "url": "https://api.getbotrank.com/mcp/free"
    }
  }
}

README

GetBotRank Free AI Search Tools (MCP)

A free, remote Model Context Protocol server that runs GetBotRank's AI search visibility checks from any MCP client. No API key, no account, and no language model behind the scores: every result comes from fixed rules or a public data source.

Endpoint: https://api.getbotrank.com/mcp/free (Streamable HTTP, no authentication)

The tools are also available as web pages at getbotrank.com/tools.

Add it to a client

Clients that accept a remote URL:

json

{  "mcpServers": {    "getbotrank-free": {      "url": "https://api.getbotrank.com/mcp/free"    }  }}

{  "mcpServers": {    "getbotrank-free": {      "url": "https://api.getbotrank.com/mcp/free"    }  }}

Clients that only speak stdio can use a bridge such as mcp-remote:

json

{  "mcpServers": {    "getbotrank-free": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://api.getbotrank.com/mcp/free"]    }  }}

{  "mcpServers": {    "getbotrank-free": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://api.getbotrank.com/mcp/free"]    }  }}

Tools

Tool	What it does
`test_robots`	Tests a URL against a site's robots.txt for 20+ crawlers (GPTBot, ClaudeBot, PerplexityBot, Googlebot, Bingbot and more) with correct longest-match rules.
`validate_schema`	Extracts JSON-LD and microdata, validates common types and returns a corrected JSON-LD block.
`check_rendering`	Estimates whether a page's content exists in the raw HTML before JavaScript runs (heuristic, no headless browser).
`preview_meta`	Reads title, description, canonical, robots, Open Graph and Twitter tags and returns data for Google, LinkedIn, X and WhatsApp previews.
`check_redirects`	Traces the redirect chain (up to 10 hops) with status and timing per hop and key response headers.
`validate_sitemap`	Finds and validates sitemaps, counts URLs, status-checks a sample of up to 50 and checks hreflang reciprocity.
`score_citability`	Scores each passage of a page for how easily answer engines can quote it. Deterministic heuristics.
`generate_og_image`	Resolves title, description and favicon for a 1200x630 social card.
`check_page_speed`	Google PageSpeed Insights: mobile and desktop scores, Core Web Vitals, field data and top fixes.
`check_common_crawl`	Checks whether a domain appears in recent Common Crawl crawls and whether robots.txt blocks CCBot.
`check_entity`	Looks up a brand on Wikidata and Wikipedia and checks Organization sameAs links.
`submit_indexnow`	Verifies an IndexNow key file and, only if it verifies, submits up to 100 URLs.
`check_ai_crawler_access`	Requests a page as several AI crawlers and as a normal browser to find robots.txt or CDN blocks.
`view_as_crawler`	Shows the text and structure a crawler recovers from a page without JavaScript.
`generate_llms_txt`	Generates an llms.txt from a domain's sitemap.
`run_free_audit`	Scores crawlability, headings, structured data, llms.txt and metadata from 0 to 100.

Every response follows one shape: { score?, summary, checks: [{ id, status, message, fix }], data, report_url }. Each failing check includes a concrete fix, and report_url links to the matching tool on getbotrank.com.

Limits and behavior

Calls are rate limited per IP (20 per 15 minutes, shared with the web tools). Some results are cached for 24 hours.
Requests to user-supplied URLs go through an SSRF-guarded fetcher that refuses private and internal addresses. Fetches identify as GetBotRankBot (see getbotrank.com/bot).
submit_indexnow never submits for a domain whose key file does not verify.

About

Built by GetBotRank, which measures whether AI engines mention your brand. This repository holds the public manifest and documentation for the hosted server.

Licensed under MIT.

来源：README.md，提交 d655ad5

工具

test_robots

Robots.txt Tester for AI Crawlers

Test one URL against a site's robots.txt for 20+ crawlers (GPTBot, ClaudeBot, PerplexityBot, Googlebot, Bingbot and more) using correct longest-match rules. Returns allowed/blocked per bot with the deciding rule.

输入参数url必填

validate_schema

Schema Markup Validator

Extract JSON-LD and microdata from a page, validate Organization, WebSite, Product, Article, FAQPage, BreadcrumbList, LocalBusiness and SoftwareApplication, and return a corrected JSON-LD block.

输入参数url必填

check_rendering

JavaScript Rendering Checker

Estimate whether a page's content exists in the raw HTML before JavaScript runs (heuristic, no headless browser). Most AI crawlers do not execute JavaScript.

输入参数url必填

preview_meta

Meta Tags and Social Preview

Read title, meta description, canonical, robots, Open Graph and Twitter tags with lengths, and return data for Google, LinkedIn, X and WhatsApp previews.

输入参数url必填

check_redirects

Redirect Chain Checker

Trace the redirect chain for a URL (max 10 hops) with status and timing per hop, plus X-Robots-Tag, HSTS, cache-control, content-type and canonical Link headers.

输入参数url必填

validate_sitemap

Sitemap Validator

Find and validate a domain's sitemaps, count URLs, status-check a sample of up to 50 URLs and check hreflang reciprocity.

输入参数domain必填

score_citability

AI Citability Analyzer

Score each passage of a page for how easily AI answer engines can quote it. Deterministic heuristics, no LLM.

输入参数url必填

generate_og_image

OG Image Generator

Resolve title, description and favicon for a 1200x630 Open Graph card from a URL or from text. Returns card data; render the PNG at the report_url.

输入参数urltitledescription

check_page_speed

PageSpeed Checker

Google PageSpeed Insights for a URL: mobile and desktop Lighthouse scores, Core Web Vitals, CrUX field data when available, top opportunities.

输入参数url必填

check_common_crawl

Is My Site in AI Training Data?

Check whether a domain appears in the latest Common Crawl crawls (a major source of LLM training data) and whether robots.txt blocks CCBot.

输入参数domain必填

check_entity

Brand Entity Checker

Look up a brand on Wikidata and Wikipedia, report key properties, and check the site's Organization sameAs links.

输入参数urlbrand必填

submit_indexnow

IndexNow Submitter

Verify an IndexNow key file on a domain and, only if it verifies, submit up to 100 URLs to api.indexnow.org. Set action to "submit" to send URLs; the default only verifies.

输入参数keyhost必填urlsaction