LangChain

The langchain-geekflare package gives LangChain agents Geekflare as a set of tools: web and Google SERP search, page scraping to Markdown or structured JSON, page metadata, brand identity, screenshots, URL-to-PDF, and website diagnostics. It’s built on the official Python SDK and requires Python 3.10+.

Install

pip install -U langchain-geekflare

Set your API key

Get an API key at dash.geekflare.com and set it as an environment variable:

export GEEKFLARE_API_KEY="YOUR_API_KEY"

Replace YOUR_API_KEY with your Geekflare API key. You can also pass the key directly to any tool with geekflare_api_key="YOUR_API_KEY".

Tools

Every tool supports invoke and async ainvoke, and returns the API’s JSON response as a dict. API errors (an invalid key, no credits, or an unreachable site) are returned to the agent as an error message instead of raising an exception.

Class	Tool name	Purpose
`GeekflareSearch`	`geekflare_search`	Web, news, and image search. Set `serp=True` for the full Google results page (AI Overview, People Also Ask) by `location` country code or `city`. Also supports `include_domains`, `exclude_domains`, `time`, `scrape`, and `grounded_answer`.
`GeekflareScrape`	`geekflare_scrape`	A page as `markdown` (default), `markdown-llm`, `text`, `html`, or `json`, using `formats`. Use `template="product"` or `template="contact"` for structured data. Also supports `render_js`, `wait_time`, and `device`.
`GeekflareMetaScrape`	`geekflare_meta_scrape`	Title, description, canonical URL, Open Graph, and Twitter Card metadata.
`GeekflareBrand`	`geekflare_brand`	Logos, colors, fonts, and social profiles. `mode="enriched"` adds company intelligence.
`GeekflareScreenshot`	`geekflare_screenshot`	A hosted image URL. Supports `full_page`, `device`, `type`, `selector`, and `theme`.
`GeekflareUrlToPdf`	`geekflare_url_to_pdf`	A hosted PDF URL. Supports `paper_format` and `orientation`.
`GeekflareSiteStatus`	`geekflare_site_status`	Check whether a site is up.
`GeekflareDnsRecords`	`geekflare_dns_records`	DNS records. Use `types` to pick record types.
`GeekflareDnsSec`	`geekflare_dnssec`	DNSSEC configuration.
`GeekflareTlsScan`	`geekflare_tls_scan`	TLS protocol support and certificate details.
`GeekflareRedirectCheck`	`geekflare_redirect_check`	The full redirect chain of a URL.
`GeekflareBrokenLinks`	`geekflare_broken_links`	Broken links on a page.
`GeekflareLoadTime`	`geekflare_load_time`	Page load time.
`GeekflareMixedContent`	`geekflare_mixed_content`	HTTP resources loaded on HTTPS pages.
`GeekflareLighthouse`	`geekflare_lighthouse`	Lighthouse audit. Supports `device`. Slower than the other tools.

Use a tool directly

from langchain_geekflare import GeekflareSearch, GeekflareScrape

search = GeekflareSearch()
search.invoke({"query": "latest stable python release", "limit": 5})
search.invoke({"query": "best project management software", "serp": True,
               "city": "London,England,United Kingdom"})

GeekflareScrape().invoke({"url": "https://example.com", "formats": ["markdown"]})

Use tools in an agent

from langchain.agents import create_agent
from langchain_geekflare import GeekflareSearch, GeekflareScrape, GeekflareTlsScan, GeekflareDnsRecords

agent = create_agent(
    model="anthropic:claude-sonnet-5-5",
    tools=[GeekflareSearch(), GeekflareScrape(), GeekflareTlsScan(), GeekflareDnsRecords()],
)
agent.invoke({"messages": [{"role": "user", "content": "Is the TLS setup on example.com healthy?"}]})

Notes

Each call spends credits from your Geekflare account. See Credit Consumption and pricing.
Geekflare works with public pages only.

PyPI

langchain-geekflare on PyPI.

GitHub

Source code (MIT license).

Python SDK

The official SDK this package is built on.

MCP Server

Connect Geekflare to AI clients through MCP.

Getting started

Quickstarts

Guides

MCP Server

Capabilities

Best Practices

Troubleshooting

Changelog

About

Install

Set your API key

Tools

Use a tool directly

Use tools in an agent

Notes

Links

PyPI

GitHub

Python SDK

MCP Server

​Install

​Set your API key

​Tools

​Use a tool directly

​Use tools in an agent

​Notes

​Links

PyPI

GitHub

Python SDK

MCP Server

Install

Set your API key

Tools

Use a tool directly

Use tools in an agent

Notes

Links