webcrawler-mcp
WebCrawlerAPI ships an official MCP server as an npm package (webcrawler-mcp) that a user runs locally over stdio, or self-hosts over HTTP with USE_HTTP=true. There is NO provider-hosted remote endpoint: the docs give no URL, mcp.webcrawlerapi.com does not resolve, and the HTTP mode in the source binds a local port (default 8080) on the user's machine. The server exposes exactly one tool, webcrawler-scrape, which POSTs to https://api.webcrawlerapi.com/v2/scrape with the user's API key from the WEBCRAWLER_API_KEY environment variable.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Descriptor
Candidate descriptor · transport stdio (default) | streamable-http (self-hosted)
Tools
webcrawler-scrape— Scrape content from a webpage using WebcrawlerAPI. Uses WEBCRAWLER_API_KEY environment variable for authentication.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.