The web scraping API for AI agents and LLMs. Send a URL, get clean Markdown, HTML or JSON back, with JavaScript rendering, structured data extraction, screenshots, and batch jobs of up to 10,000 URLs per call.
Website · Docs · Get an API key · llms.txt
| Repository | npm | What it is |
|---|---|---|
| OfficialSpicrawl/mcp |  |
MCP server: scraping, screenshots, batch jobs, login sessions, usage and docs search as 25 tools. Hosted at https://mcp.spicrawl.com/mcp, or run it locally with npx |
| OfficialSpicrawl/agent-plugins |  |
Plugins and extensions for Claude Code, Codex, Cursor, Gemini CLI, OpenCode, GitHub Copilot CLI and Factory Droid |
| OfficialSpicrawl/sdk |  |
TypeScript SDK for Node.js: typed requests and responses, retries that never double-bill, zero dependencies |
| OfficialSpicrawl/cli |  |
The spicrawl command: JSON output and stable exit codes for scripts, and one-command agent setup |
npx @spicrawl/cli scrape https://example.com --format markdown| Agent | Setup |
|---|---|
| Claude Code, Cursor, Codex, VS Code | npx @spicrawl/cli init adds the hosted MCP server and the agent skill |
| Claude Code | claude plugin marketplace add OfficialSpicrawl/agent-plugins, then claude plugin install spicrawl@spicrawl-plugins |
| Gemini CLI | gemini extensions install https://github.com/OfficialSpicrawl/agent-plugins |
| OpenCode | Add "plugin": ["opencode-spicrawl"] to opencode.json |
| Factory Droid | droid plugin marketplace add OfficialSpicrawl/agent-plugins, then droid plugin install spicrawl@spicrawl-plugins |
| Any MCP client | https://mcp.spicrawl.com/mcp with Authorization: Bearer <your API key> (guide) |
| Any Agent Skills tool | npx skills add OfficialSpicrawl/agent-plugins (skill docs) |
Every agent call runs under your API key, with the same limits and credits as a direct API call.
Spicrawl is in beta. To report a security issue, email support@spicrawl.com with "Security" in the subject, or use GitHub private vulnerability reporting on the affected repository.