Geekflare
REMOTE · MCP.GEEKFLARE.COM · 3 COMPONENTS
Web search, Google SERP, scraping, screenshots, PDFs, brand data, and website diagnostics.
Available components
Last scanned (11 hours ago)
Scores higher than 0% of remote servers
Reachable. Last reached 27 Sep 2026.
Category Web Scraping
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security0
- TLS not yet verified: the listed URL is a template whose API_KEY variable has no value or default, so there was no address for us to check.Unverified
- Authorisation not yet verified: the listed URL is a template whose API_KEY variable has no value or default, so there was no address for us to check.Unverified
- HTTPS not yet verified: the listed URL is a template whose API_KEY variable has no value or default, so there was no address for us to check. View diagnostics → Unverified
- HSTS not yet verified: the listed URL is a template whose API_KEY variable has no value or default, so there was no address for us to check.Unverified
- DNSSEC not yet verified: the listed URL is a template whose API_KEY variable has no value or default, so there was no address for us to check.Unverified
Transport & Reachability0
- Transport not yet verified: the listed URL is a template whose API_KEY variable has no value or default, so there is no address for us to connect to. See how to fix → View diagnostics → Unverified
Schema Quality & AI Usability0
- Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
- Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
- Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified
Unverified: 7 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 21 Sept 26 0
- Stability: fail → pass ▲ security
- 9 Sept 26 0
- Tool “openPorts” rewrote its description, which is the text the model reads security
- Server version: 0.4.0 → 0.4.1 functional
- New tool “brand” functional
- “openPorts” added an optional parameter “detectServices” cosmetic
- 26 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 22 Aug 26 0
- Stability: 0.87 → fail ▼ security
- Tool “ttfb” was removed ▼ security
- Tool “httpProtocol” was removed ▼ security
- Tool “httpHeader” was removed ▼ security
- Schema quality: 69 → 93 ▼ functional
- Server version: 0.3.9 → 0.4.0 functional
- “webScrape” added an optional parameter “extractionSchema” cosmetic
- “webScrape” added an optional parameter “aiPrompt” cosmetic
- “loadTime” added an optional parameter “targetCountries” cosmetic
- “webScrape” added an optional parameter “waitTime” cosmetic
- “webScrape” added an optional parameter “template” cosmetic
- “webScrape” added an optional parameter “proxyMode” cosmetic
- “webScrape” added an optional parameter “extractionMode” cosmetic
- “webScrape” reworded the description of “renderJS” cosmetic
- “webScrape” reworded the description of “proxyCountry” cosmetic
- “url2Pdf” reworded the description of “margin” cosmetic
- 11 Aug 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 31 Jul 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://mcp.geekflare.com/{API_KEY}/mcp
Transports 1 probe
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| http (plaintext) | http://mcp.geekflare.com/%7BAPI_KEY%7D/mcp | Inconclusive |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
brand ~62
Extract brand identity and design information from a website
| Name | Type | Req | Description |
|---|---|---|---|
| mode | string | – | Brand extraction mode. Enriched mode includes additional company and brand intelligence |
| refresh | boolean | – | Force refresh brand data instead of using cached data |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
brokenLink ~45
Find broken links on a webpage
| Name | Type | Req | Description |
|---|---|---|---|
| followRedirect | boolean | – | – |
| proxyCountry | string | – | Country code for proxy routing |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
dnsRecord ~31
Retrieve DNS records for a domain
| Name | Type | Req | Description |
|---|---|---|---|
| types | array | – | – |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
dnsSec ~27
Check if DNSSEC is enabled for a domain
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
lighthouse ~62
Run Lighthouse audit on a website
| Name | Type | Req | Description |
|---|---|---|---|
| device | string | – | – |
| followRedirect | boolean | – | – |
| parameters | array | – | Extra Lighthouse CLI parameters |
| proxyCountry | string | – | Country code for proxy routing |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
loadTime ~95
Measure page load time for a URL
| Name | Type | Req | Description |
|---|---|---|---|
| followRedirect | boolean | – | – |
| proxyCountry | string | – | Country code for proxy routing |
| targetCountries | array | – | Up to 3 ISO alpha-2 country codes to also test reachability from via proxy, alongside the default US server test. When set, the response includes a per-location breakdown instead of a single result |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
metaScrape ~77
Scrape meta tags from a URL
| Name | Type | Req | Description |
|---|---|---|---|
| blockAds | boolean | – | – |
| device | string | – | – |
| fileOutput | boolean | – | – |
| format | string | – | – |
| proxyCountry | string | – | Country code for proxy routing |
| renderJS | boolean | – | – |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
mixedContent ~47
Check for mixed content issues on a site
| Name | Type | Req | Description |
|---|---|---|---|
| followRedirect | boolean | – | – |
| proxyCountry | string | – | Country code for proxy routing |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
mtr ~45
Perform MTR network diagnostic test
| Name | Type | Req | Description |
|---|---|---|---|
| followRedirect | boolean | – | – |
| proxyCountry | string | – | Country code for proxy routing |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
openPorts ~89
Scan open ports on a host and optionally detect running services
| Name | Type | Req | Description |
|---|---|---|---|
| detectServices | boolean | – | Detect the service, product, version, and OS information running on discovered open ports |
| portRanges | string | – | Custom port ranges e.g. 80,443,1000-1010 |
| topPorts | number | – | Scan top N ports |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
ping ~22
Ping a host
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Target URL or IP |
No output schema declared.
No examples provided.
redirectCheck ~38
Check the redirect chain of a URL
| Name | Type | Req | Description |
|---|---|---|---|
| proxyCountry | string | – | Country code for proxy routing |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
screenshot ~315
Capture a screenshot of a website
| Name | Type | Req | Description |
|---|---|---|---|
| addTimestamp | boolean | – | – |
| blockAds | boolean | – | – |
| captureBeyondViewport | boolean | – | Allow the capture to include content beyond the configured viewport |
| delay | number | – | Seconds to wait before screenshot |
| device | string | – | – |
| disableAnimations | boolean | – | Freeze CSS/JS animations and transitions before capturing |
| fallbackToFullPage | boolean | – | If selector is not found, fall back to a full-page capture instead of failing |
| fullPage | boolean | – | – |
| hideCookie | boolean | – | Hide cookie consent banners |
| highlightLinks | boolean | – | Draw borders around links (useful for AI vision) |
| inline | boolean | – | Return image data inline instead of a CDN URL |
| pageHeight | number | – | Height of page for partial screenshot |
| proxyCountry | string | – | Country code for proxy routing |
| quality | number | – | Image quality for JPEG/WEBP |
| removeBackground | boolean | – | Remove page background for a transparent PNG (PNG only) |
| scaleFactor | number | – | Device pixel ratio |
| selector | string | – | CSS selector of the element to capture, instead of the full viewport/page |
| skipCaptcha | boolean | – | – |
| theme | string | – | Color scheme to render before capturing |
| type | string | – | – |
| url | string | yes | Target URL |
| viewportHeight | number | – | Viewport height |
| viewportWidth | number | – | Viewport width |
No output schema declared.
No examples provided.
search ~167
Search the web and return clean results in JSON, Markdown, or HTML
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | – |
| excludeDomains | array | – | Exclude these domains |
| format | string | – | – |
| groundedAnswer | boolean | – | Generate AI-grounded answer from results |
| includeDomains | array | – | Only include these domains |
| limit | number | – | Number of results |
| location | string | – | Country code (ISO alpha-2) |
| query | string | yes | Search query |
| scrape | boolean | – | Scrape content from result URLs |
| scrapeLimit | number | – | Number of URLs to scrape |
| source | string | – | – |
| time | string | – | Time filter: any, d, w, m, y, d7, h6 etc. |
No output schema declared.
No examples provided.
siteStatus ~47
Check if a site is up or down
| Name | Type | Req | Description |
|---|---|---|---|
| followRedirect | boolean | – | – |
| proxyCountry | string | – | Country code for proxy routing |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
tlsScan ~26
Scan TLS/SSL configuration of a domain
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
url2Pdf ~106
Convert a URL to PDF
| Name | Type | Req | Description |
|---|---|---|---|
| addTimestamp | boolean | – | – |
| device | string | – | – |
| format | string | – | – |
| hideCookie | boolean | – | – |
| margin | object | – | Margins in mm |
| orientation | string | – | – |
| proxyCountry | string | – | Country code for proxy routing |
| scale | number | – | Zoom level (0–2) |
| skipCaptcha | boolean | – | – |
| url | string | yes | Target URL |
No output schema declared.
No examples provided.
webScrape ~378
Scrape a webpage with custom options
| Name | Type | Req | Description |
|---|---|---|---|
| aiPrompt | object | – | AI-powered extraction/analysis of the scraped page, always run against the Markdown regardless of format. Shape depends on 'type': prompt (query), schema (schema), listing (itemSchema, maxItems), sum… |
| blockAds | boolean | – | – |
| device | string | – | – |
| extractionMode | string | – | Only used if format includes json |
| extractionSchema | object | – | Extraction schema for cssSchema/xpathSchema modes: { name, baseSelector?, fields: [{ name, selector, type, attribute?, fields? }] }, or a flat { name, fields: [{ title, value }] } for default mode |
| fileOutput | boolean | – | Return a download URL instead of inline data |
| format | array | – | Output format(s). Up to 3. |
| proxyCountry | string | – | Country code for proxy routing (used when a proxy is active) |
| proxyMode | – | – | false never uses a proxy (default), auto tries without a proxy first and retries through one if blocked, true always uses a proxy |
| renderJS | boolean | – | Whether to render JavaScript. If omitted, resolved automatically: fetched without a browser first, then rendered only if the page needs it |
| stealth | boolean | – | Bypass CAPTCHAs (slower) |
| template | string | – | Ready-made extraction template when extractionMode is 'template'. product extracts title/brand/pricing/availability/images/ratings; contact extracts company/locations/emails/phones/social profiles |
| url | string | yes | Target URL |
| waitTime | number | – | Seconds to wait after page load before capturing content |
No output schema declared.
No examples provided.
How do I install the Geekflare MCP server?
Geekflare is a hosted endpoint at https://mcp.geekflare.com/%7BAPI_KEY%7D/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · mcp.geekflare.com
claude mcp add --transport http com-geekflare-mcp 'https://mcp.geekflare.com/%7BAPI_KEY%7D/mcp'
What is the Geekflare MCP server?
Geekflare is an MCP server listed in the public MCP registry as com.geekflare/mcp. Web search, Google SERP, scraping, screenshots, PDFs, brand data, and website diagnostics. This page covers its hosted endpoint (https://mcp.geekflare.com/{API_KEY}/mcp).
Is the Geekflare MCP server safe to use?
Geekflare scores 0 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Geekflare MCP server expose?
Geekflare exposes 18 tools: webScrape, metaScrape, screenshot, search, dnsRecord, and 13 more. Their descriptions and schemas cost roughly 1,679 tokens of context every time the server is loaded.
Does the Geekflare MCP server require authentication?
Its publisher declares no required credentials for Geekflare. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.
Is the Geekflare MCP server still maintained?
Geekflare is still listed as active in the MCP registry. We last reached this channel on 27 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.