Official MCP (Model Context Protocol) server for the Geekflare. Connect Geekflare's web intelligence tools directly to Claude, Cursor, Windsurf, and other AI assistants.
geekflare-api-mcp is an MCP project maintained in the geekflare/geekflare-api-mcp repository. The maintainer describes its purpose as “Official MCP (Model Context Protocol) server for the Geekflare. Connect Geekflare's web intelligence tools directly to Claude, Cursor, Windsurf, and other AI assistants”. Read the project documentation for the complete scope.
The documented npm package is @geekflare/mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares API_KEY. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| standard | Returns structured brand information available from the website. |
| enriched | Includes additional LLM-synthesized company intelligence when available. |
| device | desktop |
| format | a4 |
| proxyMode | boolean |
| proxyCountry | string |
| renderJS | boolean |
| fileOutput | boolean |
| blockAds | boolean |
| stealth | boolean |
| waitTime | number |
| extractionMode | default |
| template | product |
| extractionSchema | object |
| aiPrompt | object |
| refresh | boolean |
| mode | standard |
| fullPage | boolean |
| selector | string |
| fallbackToFullPage | boolean |
| hideCookie | boolean |
| skipCaptcha | boolean |
| addTimestamp | boolean |
| highlightLinks | boolean |
| pageHeight | number |
| viewportWidth | number |
| viewportHeight | number |
| captureBeyondViewport | boolean |
| delay | number |
| quality | number |
| scaleFactor | number |
| theme | light |
| removeBackground | boolean |
| disableAnimations | boolean |
| inline | boolean |
| limit | number |
| time | string |
| location | string |
| source | web |
| category | general |
| includeDomains | array |
| excludeDomains | array |
| groundedAnswer | boolean |
| scrape | boolean |
| scrapeLimit | number |
| types | array |
| followRedirect | boolean |
| orientation | portrait |
| scale | number |
| margin.top | number |
| margin.bottom | number |
| margin.left | number |
| margin.right | number |
| topPorts | 50 |
| portRanges | string |
| detectServices | boolean |
| targetCountries | array of string |
| parameters | array of string |
{
"mcpServers": {
"geekflare": {
"command": "npx",
"args": [
"-y",
"@geekflare/mcp"
],
"env": {
"API_KEY": "YOUR_API_KEY"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| API_KEY | Declared in the maintainer’s client configuration. | Check documentation |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
Mantic is a context-aware code search engine that prioritizes relevance over raw speed. After testing across 5 repositories (cal.com, next.js, tensorflow, supabase, chromium), it demonstrates…
Live web search for AI agents. $0.001/call, x402 on Base, no API key.
An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Video Search, Image Search, News Search and LLM Context Search capabilities
MCP server providing Google Search, web scraping, and multi-source research tools for AI assistants