WebCrawlerAPI

WebCrawlerAPI MCP Server

Official Model Context Protocol server distributed as the npm package webcrawler-mcp (npx -y webcrawler-mcp) and run locally over stdio - or self-hosted over streamable HTTP with USE_HTTP=true - by the user; there is no provider-hosted remote endpoint. It exposes one tool, webcrawler-scrape (url, optional prompt, optional main_content_only), which POSTs to https://api.webcrawlerapi.com/v2/scrape with the API key from the WEBCRAWLER_API_KEY environment variable and returns markdown (or structured_data when a prompt is set). Source: github.com/WebCrawlerAPI/webcrawlerapi-mcp.

GitHub

Documentation

📖
Documentation
https://webcrawlerapi.com/docs/sdk/mcp

Other Resources

🔗
MCPServer
https://raw.githubusercontent.com/api-evangelist/webcrawlerapi-com/refs/heads/main/mcp/webcrawlerapi-com-mcp.yml
🔗
MCPServer
https://www.npmjs.com/package/webcrawler-mcp
🔗
ToolCrosswalk
https://raw.githubusercontent.com/api-evangelist/webcrawlerapi-com/refs/heads/main/mcp/webcrawlerapi-com-tool-crosswalk.yml
🔗
SourceCode
https://github.com/WebCrawlerAPI/webcrawlerapi-mcp

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/webcrawlerapi-mcp-server"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

API entry from apis.yml

apis.yml Raw ↑ 
aid: webcrawlerapi-com:webcrawlerapi-mcp-server
name: WebCrawlerAPI MCP Server
description: 'Official Model Context Protocol server distributed as the npm package webcrawler-mcp (npx
  -y webcrawler-mcp) and run locally over stdio - or self-hosted over streamable HTTP with USE_HTTP=true
  - by the user; there is no provider-hosted remote endpoint. It exposes one tool, webcrawler-scrape (url,
  optional prompt, optional main_content_only), which POSTs to https://api.webcrawlerapi.com/v2/scrape
  with the API key from the WEBCRAWLER_API_KEY environment variable and returns markdown (or structured_data
  when a prompt is set). Source: github.com/WebCrawlerAPI/webcrawlerapi-mcp.'
humanURL: https://webcrawlerapi.com/docs/sdk/mcp
baseURL: https://api.webcrawlerapi.com
tags:
- MCP
- AI Agents
- Web Scraping
- Agent-Native
tags_raw:
- MCP
- AI Agents
- Web Scraping
- agent-native
properties:
- type: MCPServer
  url: mcp/webcrawlerapi-com-mcp.yml
- type: MCPServer
  name: webcrawler-mcp on npm (local stdio package)
  url: https://www.npmjs.com/package/webcrawler-mcp
- type: ToolCrosswalk
  url: mcp/webcrawlerapi-com-tool-crosswalk.yml
- type: Documentation
  url: https://webcrawlerapi.com/docs/sdk/mcp
- type: SourceCode
  url: https://github.com/WebCrawlerAPI/webcrawlerapi-mcp
image: https://webcrawlerapi.com/favicon.png