Crawl, search, and extract as agent tools.
Spider lets your agents crawl, search, and extract through a single API or MCP server. Returns clean markdown that fits in context windows without burning tokens on HTML.
-
spider_crawlFollow links across a site, return content. -
spider_scrapeGrab one page, no link following. -
spider_searchSearch the web, optionally crawl results. -
spider_linksList every link on a page. -
spider_screenshotFull-page or viewport screenshot. -
spider_transformConvert HTML to markdown locally.
One command to web-enable your AI.
Add Spider as an MCP server and your AI tool gets crawling, search, and extraction out of the box. No wrapper code needed.
# Claude Code claude mcp add spider -- npx -y spider-cloud-mcp
{
"mcpServers": {
"spider": {
"command": "npx",
"args": ["-y", "spider-cloud-mcp"],
"env": {
"SPIDER_API_KEY": "your-api-key"
}
}
}
}What your agent gets out of the box.
Read entire websites
Submit a URL, get clean markdown for every page. No HTML parsing. Output is token-efficient and fits directly in context.
Query the live web
Search the web and optionally crawl results in the same request. Ground agent responses in live data instead of training-cutoff knowledge.
Pull structured data
Set extra_ai_data: true with a custom_prompt and Spider extracts data matching your description. Or use css_extraction_map for CSS/XPath selectors.
Interact with pages
The Browser API provides a CDP WebSocket connection: navigate, click, type, scroll, capture screenshots. Use the spider_ai_browser MCP tool for natural-language automation.
Native tool for AI IDEs
Install the MCP server and Claude, Cursor, or Windsurf can call Spider directly. One command setup, zero config files to maintain.
Drop-in agent tools
Published integrations for LangChain (document loader) and CrewAI (SpiderTool). The REST API and Python/Node SDKs work with any framework.
Drop into the framework you already use.
from crewai_tools import SpiderTool
spider = SpiderTool()
agent = Agent(
role="Research Analyst",
tools=[spider],
goal="Find and summarize data",
)from langchain_community.document_loaders \
import SpiderLoader
loader = SpiderLoader(
url="https://docs.example.com",
mode="crawl",
)
docs = loader.load()Keep reading.
Your agent is one command from the live web.
Add Spider as an MCP tool and start crawling. No credit card required.