Geekflare
Geekflare MCP server connects your AI agents to the live web for scraping, search, screenshots, DNS lookup, site uptime and more.
README
@geekflare/mcp
Official MCP (Model Context Protocol) server for the Geekflare API. Connect Geekflare's web intelligence tools directly to Claude, Cursor, Windsurf, and other AI assistants.
Setup
Get an API Key
Sign up at geekflare.com/api and copy your API key from the dashboard.
Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"geekflare": {
"command": "npx",
"args": ["-y", "@geekflare/mcp"],
"env": {
"API_KEY": "your-api-key-here"
}
}
}
}
Cursor / Windsurf
Add to your MCP settings:
{
"mcpServers": {
"geekflare": {
"command": "npx",
"args": ["-y", "@geekflare/mcp"],
"env": {
"API_KEY": "your-api-key-here"
}
}
}
}
Docker
{
"mcpServers": {
"geekflare": {
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "API_KEY=your-api-key-here", "geekflare/mcp"]
}
}
}
Available Tools
webScrape
Scrape full page content from any URL. Returns HTML, Markdown, JSON, or LLM-optimised text.
| Parameter | Type | Default | Description |
|---|---|---|---|
url * |
string | — | Target URL |
device |
desktop | mobile |
desktop |
Device to emulate |
format |
array | ["markdown"] |
Output formats (up to 3): html, markdown, json, markdown-llm, html-llm, text, text-llm |
proxyCountry |
string | — | Route through a country ISO code (e.g. "us") |
renderJS |
boolean | true |
Execute JavaScript before extracting. Disable for faster static scrapes |
fileOutput |
boolean | false |
Return a download URL instead of inline content |
blockAds |
boolean | true |
Block ads during scrape |
stealth |
boolean | false |
Bypass CAPTCHAs (slower) |
metaScrape
Scrape meta tags — title, description, Open Graph, Twitter cards, and more.
| Parameter | Type | Default | Description |
|---|---|---|---|
url * |
string | — | Target URL |
device |
desktop | mobile |
desktop |
|
format |
json | markdown |
json |
|
proxyCountry |
string | — | Country ISO code |
renderJS |
boolean | true |
|
fileOutput |
boolean | false |
|
blockAds |
boolean | true |
screenshot
Capture a screenshot of any website. Supports full-page, Retina, and AI-friendly link highlighting.
| Parameter | Type | Default | Description |
|---|---|---|---|
url * |
string | — | Target URL |
device |
desktop | mobile |
desktop |
|
type |
png | jpeg | webp |
png |
|
proxyCountry |
string | — | Country ISO code |
fullPage |
boolean | false |
|
blockAds |
boolean | true |
|
hideCookie |
boolean | true |
Remove cookie banners |
skipCaptcha |
boolean | true |
Bypass Cloudflare / reCAPTCHA |
addTimestamp |
boolean | false |
|
highlightLinks |
boolean | false |
Draw borders around links/buttons — great for AI vision models |
pageHeight |
number | — | Custom page height (px) |
viewportWidth |
number | — | Viewport width (px, default 1366) |
viewportHeight |
number | — | Viewport height (px, default 768) |
delay |
number | — | Seconds to wait after page load |
quality |
number | 90 |
Image quality 1–100 |
scaleFactor |
number | — | Device pixel ratio (use 2–3 for Retina) |
search
Search the web and return clean, structured results. Supports web, news, and image search with optional AI-grounded answers.
| Parameter | Type | Default | Description |
|---|---|---|---|
query * |
string | — | Search query |
limit |
number | 10 |
Number of results |
time |
string | — | Time filter: any, d, w, m, y, d7, h6 |
location |
string | — | Country ISO code to localise results |
source |
web | news | images |
web |
|
category |
general | code | research |
— | |
format |
json | markdown | html |
json |
|
includeDomains |
string | — | Comma-separated domains to include |
excludeDomains |
string | — | Comma-separated domains to exclude |
groundedAnswer |
boolean | false |
Generate an AI answer synthesised from results |
scrape |
boolean | — | Also scrape top result pages |
scrapeLimit |
number | — | How many pages to scrape (requires scrape: true) |
dnsRecord
Look up DNS records for a domain.
| Parameter | Type | Default |
|---|---|---|
url * |
string | — |
types |
array of A AAAA CNAME MX NS SOA TXT CAA SRV |
all types |
siteStatus
Check if a site is up or down.
| Parameter | Type | Default |
|---|---|---|
url * |
string | — |
proxyCountry |
string | — |
followRedirect |
boolean | false |
redirectCheck
Trace the full redirect chain of a URL.
| Parameter | Type |
|---|---|
url * |
string |
proxyCountry |
string |
brokenLink
Find all broken links on a webpage.
| Parameter | Type | Default |
|---|---|---|
url * |
string | — |
proxyCountry |
string | — |
followRedirect |
boolean | false |
url2Pdf
Convert any URL to a downloadable PDF.
| Parameter | Type | Default | Description |
|---|---|---|---|
url * |
string | — | |
device |
desktop | mobile |
desktop |
|
format |
a4 a3 a5 a6 letter legal a0–a2 |
a4 |
Paper size |
orientation |
portrait | landscape |
portrait |
|
proxyCountry |
string | — | Country ISO code |
scale |
number | — | Zoom level (e.g. 0.8 to shrink) |
margin.top |
number | 25 |
Top margin (mm) |
margin.bottom |
number | 25 |
Bottom margin (mm) |
margin.left |
number | 25 |
Left margin (mm) |
margin.right |
number | 25 |
Right margin (mm) |
hideCookie |
boolean | true |
Remove cookie banners |
skipCaptcha |
boolean | true |
Bypass anti-bot challenges |
addTimestamp |
boolean | false |
openPorts
Scan open ports on a host.
| Parameter | Type | Description |
|---|---|---|
url * |
string | Target URL or hostname |
topPorts |
50 100 500 1000 5000 |
Scan top N common ports |
portRanges |
string | Custom ranges e.g. "80,443,1000-1010" |
tlsScan
Inspect TLS/SSL configuration — protocols, ciphers, certificate details.
| Parameter | Type |
|---|---|
url * |
string |
loadTime
Measure full page load time from any location.
| Parameter | Type | Default |
|---|---|---|
url * |
string | — |
proxyCountry |
string | — |
followRedirect |
boolean | false |
ttfb
Measure Time To First Byte (TTFB).
| Parameter | Type | Default |
|---|---|---|
url * |
string | — |
followRedirect |
boolean | false |
httpHeader
Retrieve HTTP response headers for a URL.
| Parameter | Type | Default |
|---|---|---|
url * |
string | — |
proxyCountry |
string | — |
followRedirect |
boolean | false |
httpProtocol
Check which HTTP protocol versions (HTTP/1.1, HTTP/2, HTTP/3) a server supports.
| Parameter | Type | Default |
|---|---|---|
url * |
string | — |
followRedirect |
boolean | false |
mixedContent
Detect mixed content issues (HTTP resources on HTTPS pages).
| Parameter | Type | Default |
|---|---|---|
url * |
string | — |
proxyCountry |
string | — |
followRedirect |
boolean | false |
dnsSec
Check if DNSSEC is enabled and properly configured for a domain.
| Parameter | Type |
|---|---|
url * |
string |
mtr
Run an MTR (My Traceroute) network diagnostic test.
| Parameter | Type | Default |
|---|---|---|
url * |
string | — |
proxyCountry |
string | — |
followRedirect |
boolean | false |
ping
Ping a host and return latency.
| Parameter | Type |
|---|---|
url * |
string |
lighthouse
Run a full Lighthouse audit — performance, SEO, accessibility, and best practices.
| Parameter | Type | Default | Description |
|---|---|---|---|
url * |
string | — | |
device |
desktop | mobile |
desktop |
|
proxyCountry |
string | — | Country ISO code |
followRedirect |
boolean | false |
|
parameters |
string | — | Extra Lighthouse CLI flags (e.g. "--only-categories=seo") |
Environment Variables
| Variable | Required | Description |
|---|---|---|
API_KEY |
✅ | Your Geekflare API key |
API_BASE_URL |
— | Override the API base URL (default: https://api.geekflare.com) |
Links
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。