LlamaIndex

The llama-index-tools-geekflare package gives LlamaIndex agents Geekflare as a tool spec: 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+ and llama-index-core 0.12 to 0.14.

Install

pip install llama-index-tools-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 with GeekflareToolSpec(api_key="YOUR_API_KEY"). An optional timeout (in seconds, default 180) controls how long each call can run.

Use the tools in an agent

GeekflareToolSpec().to_tool_list() returns all 15 tools.

from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.anthropic import Anthropic
from llama_index.tools.geekflare import GeekflareToolSpec

agent = FunctionAgent(
    tools=GeekflareToolSpec().to_tool_list(),
    llm=Anthropic(model="claude-sonnet-5-5"),
)
response = await agent.run("Is the TLS certificate on example.com close to expiring?")
print(response)

Select only the tools you need

Give the agent only the tools it needs by filtering on the tool name:

spec = GeekflareToolSpec()
tools = [t for t in spec.to_tool_list() if t.metadata.name in {"search", "scrape"}]

Call tools directly

from llama_index.tools.geekflare import GeekflareToolSpec

geekflare = GeekflareToolSpec()
geekflare.search("latest stable python release", limit=5)
geekflare.search("best project management software", serp=True,
                 city="London,England,United Kingdom")
geekflare.scrape("https://example.com", formats=["markdown"])

Tools

Each tool returns the API’s JSON response as a dict. API errors raise GeekflareAPIError, which agents receive as a tool error.

Tool name	Purpose and key arguments
`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 `limit`, `source`, `time`, `include_domains`, `exclude_domains`, `scrape`, and `grounded_answer`.
`scrape`	Page content 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`.
`meta_scrape`	Title, description, canonical URL, Open Graph, and Twitter Card metadata.
`brand`	Logos, colors, fonts, and social profiles. `mode="enriched"` adds company intelligence.
`screenshot`	A hosted image URL. Supports `full_page`, `device`, `image_type`, and `selector`.
`url_to_pdf`	A hosted PDF URL. Supports `paper_format` and `orientation`.
`site_status`	Check whether a site is up.
`dns_records`	DNS records. Use `types` to pick record types.
`dnssec`	DNSSEC configuration.
`tls_scan`	TLS protocol support and certificate details.
`redirect_check`	The full redirect chain of a URL.
`broken_links`	Broken links on a page.
`load_time`	Page load time.
`mixed_content`	HTTP resources loaded on HTTPS pages.
`lighthouse`	Lighthouse audit. Supports `device`. Slower than the other tools.

Notes

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

PyPI

llama-index-tools-geekflare on PyPI.

GitHub

Source code (MIT license).

Python SDK

The official SDK this package is built on.

LangChain

Use Geekflare tools in LangChain agents.

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

Use the tools in an agent

Select only the tools you need

Call tools directly

Tools

Notes

Links

PyPI

GitHub

Python SDK

LangChain

MCP Server

​Install

​Set your API key

​Use the tools in an agent

​Select only the tools you need

​Call tools directly

​Tools

​Notes

​Links

PyPI

GitHub

Python SDK

LangChain

MCP Server

Install

Set your API key

Use the tools in an agent

Select only the tools you need

Call tools directly

Tools

Notes

Links