{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_p93q5zmv8zb6","handle":"crawl4ai-mcp-server","url":"https://wellknown.network/agents/crawl4ai-mcp-server","links":{"self":"https://wellknown.network/agents/crawl4ai-mcp-server/record.json","html":"https://wellknown.network/agents/crawl4ai-mcp-server","markdown":"https://wellknown.network/agents/crawl4ai-mcp-server/record.md","api":"https://wellknown.network/api/v1/agents/crawl4ai-mcp-server","status":"https://wellknown.network/api/v1/agents/crawl4ai-mcp-server/status","claim":"https://wellknown.network/agents/crawl4ai-mcp-server/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/crawl4ai-mcp-server/claim.json","badge":"https://wellknown.network/agents/crawl4ai-mcp-server/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/crawl4ai-mcp-server/history","tools":"https://wellknown.network/api/v1/agents/crawl4ai-mcp-server/tools"},"ard":{"identifier":"urn:air::server:crawl4ai-mcp-server","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"crawl4ai-mcp-server","summary":"A Model Context Protocol server for web crawling using Crawl4ai","description":"# Crawl4AI MCP Server\n\nA Model Context Protocol server for web crawling using the Crawl4ai library.\n\n## 📋 Overview\n\nCrawl4AI MCP Server provides a set of tools and prompts for web crawling through the Model Context Protocol (MCP). It allows AI assistants to autonomously crawl websites, extract content, and save information as Markdown files.\n\n## ✨ Features\n\n- 🕸️ **Single Page Crawling**: Extract content from a single webpage in Markdown format\n- 🌐 **Deep Website Crawling**: Crawl multiple pages of a website with configurable depth and limits\n- 🔍 **Structured Data Extraction**: Use CSS selectors to extract specific structured data from webpages\n- 💾 **Markdown Export**: Save crawled content directly as Markdown files\n\n## 🚀 Installation\n\n```bash\npip install crawl4ai-mcp-server\n```\n\n## 🛠️ Usage\n\n### Command Line\n\nRun the server directly from the command line:\n\n```bash\ncrawl4ai-mcp\n```\n\n### Python API\n\n```python\nimport asyncio\nfrom crawl4ai_mcp import serve\n\n# Run the server\nasyncio.run(serve())\n```\n\n## 📝 Available Tools\n\n### crawl_webpage\n\nCrawls a single webpage and returns its content as markdown.\n\n**Parameters**:\n\n- `url` (string, required): URL to crawl\n- `include_images` (boolean, optional): Whether to include images in the result (default: true)\n- `bypass_cache` (boolean, optional): Whether to bypass cache (default: false)\n\n### crawl_website\n\nCrawls a website starting from the given URL, with specified depth and page limit.\n\n**Parameters**:\n\n- `url` (string, required): Starting URL\n- `max_depth` (integer, optional): Maximum crawl depth (default: 1)\n- `max_pages` (integer, optional): Maximum number of pages to crawl (default: 5)\n- `include_images` (boolean, optional): Whether to include images (default: true)\n\n### extract_structured_data\n\nExtracts structured data from a webpage using CSS selectors.\n\n**Parameters**:\n\n- `url` (string, required): URL to extract data from\n- `schema` (object, optional): Schema defining what to extract\n- `css_selector` (string, …","publisher":null,"homepage":"https://github.com/yourusername/crawl4ai-mcp-server","repository":"https://github.com/yourusername/crawl4ai-mcp-server/issues","version":"0.1.5","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:crawl4ai-mcp-server","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"documents.extraction","name":"Data Extraction","confidence":0.894,"provenance":"derived"},{"slug":"dev.terminal","name":"Terminal & Shell","confidence":0.825,"provenance":"derived"}],"categories":["dev","documents"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"crawl4ai-mcp-server","registry":"pypi","observedAt":"2026-10-27T22:27:54.178Z","publishedAt":"2025-05-04T17:09:31.443527Z","latestVersion":"0.1.5"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"crawl4ai-mcp-server","url":"https://pypi.org/project/crawl4ai-mcp-server/","firstSeenAt":"2026-09-09T13:20:42.261Z","fetchedAt":"2026-10-27T22:27:04.363Z","normalizedAt":"2026-10-27T22:27:04.363Z"}]},"firstSeenAt":"2026-09-09T13:20:42.261Z","updatedAt":"2026-10-27T22:27:54.178Z"}