XCrawl
Web extraction REST API with remote MCP and a published Node.js CLI
XCrawl provides scrape, search, map, and crawl APIs for web-data workflows. The documented REST base is https://run.xcrawl.com and requests use a bearer API key. Outputs can include structured JSON, Markdown, HTML, and screenshots. See https://docs.xcrawl.com/doc/api-reference/overview/. Its remote MCP uses an API-key-bearing URL documented at https://docs.xcrawl.com/doc/developer-guides/claude-code-mcp/; keep that configuration private. Initialization and tool discovery returned seven tools. The published @xcrawl/cli package was version 0.3.3 with Node.js 18 or later at review; the documentation still showed 0.2.7. npm package integrity was checked without executing the package. No public OpenAPI contract or working SDK package was verified, despite SDK claims on the website. The provider advertises 1,000 introductory signup credits and paid plans at https://www.xcrawl.ai/buy/. The credit grant and paid prices were not tested. REST rejected a request without credentials; an MCP call with a deliberately invalid test key returned a credit error, not scraped data. Authenticated extraction, SDK execution, and billing were not tested.
Best for agent capabilities
Useful in agent tasks
Overview
When to use XCrawl
XCrawl is listed for Web Scraping, Search, Data workflows. XCrawl provides scrape, search, map, and crawl APIs for web-data workflows. The documented REST base is https://run.xcrawl.com and requests use a bearer API key. Outputs can include structured JSON, Markdown, HTML, and screenshots. See https://docs.xcrawl.com/doc/api-reference/overview/. Its remote MCP uses an API-key-bearing URL documented at https://docs.xcrawl.com/doc/developer-guides/claude-code-mcp/; keep that configuration private. Initialization and tool discovery returned seven tools. The published @xcrawl/cli package was version 0.3.3 with Node.js 18 or later at review; the documentation still showed 0.2.7. npm package integrity was checked without executing the package. No public OpenAPI contract or working SDK package was verified, despite SDK claims on the website. The provider advertises 1,000 introductory signup credits and paid plans at https://www.xcrawl.ai/buy/. The credit grant and paid prices were not tested. REST rejected a request without credentials; an MCP call with a deliberately invalid test key returned a credit error, not scraped data. Authenticated extraction, SDK execution, and billing were not tested. Consider it when an agent needs this capability through a documented service boundary instead of custom infrastructure maintained inside the application.
In 4agent’s task model, the product maps to Web search, Web extraction, Workflow automation. That makes it a candidate for these tasks: Research the web, Manage memory and knowledge, Communicate with users, Automate business workflows.
Integration checklist
- Access: Confirm the api key authentication flow, credential scope, rotation process, and whether calls can be attributed to a user or service identity.
- Client support: No SDK is recorded, so verify the HTTP API or another supported integration path.
- Automation: OpenAPI: not currently recorded; MCP: listed as available; CLI: listed as available. Confirm each requirement in the provider's current documentation.
- Operations: Test rate limits, timeouts, retry safety, error payloads, logs, data retention, and the current free-tier and paid pricing model with production-like volume.
Sources and verification
Use these primary sources to verify current behavior before making an implementation or purchasing decision. Product capabilities, limits, and prices can change after a 4agent listing is reviewed.