Name: ScrAPI MCP Server
Author: DevEnterpriseSoftware

LABSCO SUMMARY

The blocked-page problem handed to a service, with the output format as the only real decision.

scrape_url_html and scrape_url_markdown take the same two parameters and differ in what they hand back, so the choice is made on what you plan to do next: parse the markup, or read the prose. The surface stops there — one URL per call, with browserCommands as the single lever for pages that only reveal their content after a click or a scroll.

What it is

A two-tool front end to the ScrAPI scraping service, one tool per output format, both taking the same URL.

What you get

Website content reached through ScrAPI where bot detection, captchas or geolocation restrictions stand in the way of a direct fetch
HTML output when advanced parsing is required, and Markdown when the text content matters and the page structure does not
An optional browserCommands list that interacts with the page before the content is taken

Requirements

A ScrAPI key in SCRAPI_API_KEY. Pages are addressed one URL at a time, and the browserCommands list is the only way to reach content that appears after an interaction.

Setup effort

One command — npx -y @deventerprisesoftware/scrapi-mcp

See installation options

USE CASES

Reading a page that answers your own request with a captcha

Send the URL through the service instead of fetching it directly, and take Markdown when you want the prose or HTML when you intend to parse the markup.

scrape_url_markdownscrape_url_html

Reaching content that only appears after an interaction

Attach browser commands to the request so the page is acted on before its content is taken, then keep the markup for parsing.

scrape_url_html

2 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`scrape_url_html`

Use a URL to scrape a website using the ScrAPI service and retrieve the result as HTML. Use this for scraping website content that is difficult to access because of bot detection, captchas or even geolocation restrictions. The result will be in HTML which is preferable if advanced parsing is required.

BROWSER COMMANDS: You can optionally provide browser commands to interact with the page before scraping (e.g., clicking buttons, filling forms, scrolling). Provide commands as a JSON array string. Available commands:

Click: {"click": "#buttonId"} - Click an element using CSS selector
Input: {"input": {"input[name='email']": "value"}} - Fill an input field
Select: {"select": {"select[name='country']": "USA"}} - Select from dropdown
Scroll: {"scroll": 1000} - Scroll down (negative values scroll up)
Wait: {"wait": 5000} - Wait milliseconds (max 15000)
WaitFor: {"waitfor": "#elementId"} - Wait for element to appear
JavaScript: {"javascript": "console.log('test')"} - Execute custom JS

Example: [{"click": "#accept-cookies"}, {"wait": 2000}, {"input": {"input[name='search']": "query"}}]

INSTALLATION

Connect your client

Server setup

TERMINAL

npx -y @deventerprisesoftware/scrapi-mcp

MCP Clients

Claude Desktop — npx, Any MCP client — stdio

JSON

{
  "mcpServers": {
    "ScrAPI": {
      "command": "npx",
      "args": [
        "-y",
        "@deventerprisesoftware/scrapi-mcp"
      ],
      "env": {
        "SCRAPI_API_KEY": "<YOUR_SCRAPI_API_KEY>"
      }
    }
  }
}

Claude Desktop — Docker

CLAUDE DESKTOP — DOCKER · JSON

{
  "mcpServers": {
    "ScrAPI": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SCRAPI_API_KEY",
        "deventerprisesoftware/scrapi-mcp"
      ],
      "env": {
        "SCRAPI_API_KEY": "<YOUR_SCRAPI_API_KEY>"
      }
    }
  }
}

Cursor — stdio, Windsurf — stdio

JSON

{
  "mcpServers": {
    "scrapi": {
      "command": "npx",
      "args": [
        "-y",
        "@deventerprisesoftware/scrapi-mcp"
      ],
      "env": {
        "SCRAPI_API_KEY": "${env:SCRAPI_API_KEY}"
      }
    }
  }
}

Your editor fills in ${env:SCRAPI_API_KEY} from your environment: set SCRAPI_API_KEY to your ScrAPI key before you start it.

Cursor — HTTP

Start the server in HTTP mode first

CURSOR — HTTP · TERMINAL

TRANSPORT=http PORT=5000 SCRAPI_API_KEY="<YOUR_SCRAPI_API_KEY>" npx -y @deventerprisesoftware/scrapi-mcp

Then point the client at http://localhost:5000/mcp

CURSOR — HTTP · JSON

{
  "mcpServers": {
    "scrapi": {
      "url": "http://localhost:5000/mcp"
    }
  }
}

Windsurf — HTTP

Start the server in HTTP mode first

WINDSURF — HTTP · TERMINAL

TRANSPORT=http PORT=5000 SCRAPI_API_KEY="<YOUR_SCRAPI_API_KEY>" npx -y @deventerprisesoftware/scrapi-mcp

Then point the client at http://localhost:5000/mcp

WINDSURF — HTTP · JSON

{
  "mcpServers": {
    "scrapi": {
      "serverUrl": "http://localhost:5000/mcp"
    }
  }
}

Kilo Code — npx

KILO CODE — NPX · JSON

{
  "mcp": {
    "scrapi": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@deventerprisesoftware/scrapi-mcp"
      ],
      "environment": {
        "SCRAPI_API_KEY": "<YOUR_SCRAPI_API_KEY>"
      },
      "enabled": true,
      "timeout": 300000
    }
  }
}

Kilo Code — remote

Start the server in HTTP mode first

KILO CODE — REMOTE · TERMINAL

TRANSPORT=http PORT=5000 SCRAPI_API_KEY="<YOUR_SCRAPI_API_KEY>" npx -y @deventerprisesoftware/scrapi-mcp

Then point the client at http://localhost:5000/mcp

KILO CODE — REMOTE · JSON

{
  "mcp": {
    "scrapi": {
      "type": "remote",
      "url": "http://localhost:5000/mcp",
      "enabled": true,
      "timeout": 300000
    }
  }
}

Codex

CODEX · TOML

[mcp_servers.scrapi]
command = "npx"
args = ["-y", "@deventerprisesoftware/scrapi-mcp"]
startup_timeout_sec = 20
tool_timeout_sec = 300

[mcp_servers.scrapi.env]
SCRAPI_API_KEY = "<YOUR_SCRAPI_API_KEY>"

VS Code

VS CODE · JSON

{
  "inputs": [
    {
      "type": "promptString",
      "id": "scrapi-api-key",
      "description": "ScrAPI API key",
      "password": true
    }
  ],
  "servers": {
    "scrapi": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@deventerprisesoftware/scrapi-mcp"
      ],
      "env": {
        "SCRAPI_API_KEY": "${input:scrapi-api-key}"
      }
    }
  }
}

Claude Code — stdio

CLAUDE CODE — STDIO · TERMINAL

claude mcp add --transport stdio --env SCRAPI_API_KEY="<YOUR_SCRAPI_API_KEY>" scrapi -- npx -y @deventerprisesoftware/scrapi-mcp

Claude Code — HTTP

Start the server in HTTP mode first

CLAUDE CODE — HTTP · TERMINAL

TRANSPORT=http PORT=5000 SCRAPI_API_KEY="<YOUR_SCRAPI_API_KEY>" npx -y @deventerprisesoftware/scrapi-mcp

Then point the client at http://localhost:5000/mcp

CLAUDE CODE — HTTP · TERMINAL

claude mcp add --transport http scrapi http://localhost:5000/mcp

Any MCP client — hosted

URL: https://api.scrapi.tech/mcp

Auth: query parameter ?apiKey=<YOUR_SCRAPI_API_KEY> or request header X-API-KEY: <YOUR_SCRAPI_API_KEY>

ScrAPI MCP Server

The blocked-page problem handed to a service, with the output format as the only real decision.

What it is

What you get

Requirements

Setup effort

Reading a page that answers your own request with a captcha

Reaching content that only appears after an interaction

2 tools

`scrape_url_html`

`scrape_url_markdown`

What to know first

Tools you get

Requires

Light Standing cost

Connect your client

Server setup

MCP Clients

Claude Desktop — npx, Any MCP client — stdio

Claude Desktop — Docker

Cursor — stdio, Windsurf — stdio

Cursor — HTTP

Windsurf — HTTP

Kilo Code — npx

Kilo Code — remote

Codex

VS Code

Claude Code — stdio

Claude Code — HTTP

Any MCP client — hosted

ScrAPI MCP Server

The blocked-page problem handed to a service, with the output format as the only real decision.

What it is

What you get

Requirements

Setup effort

Reading a page that answers your own request with a captcha

Reaching content that only appears after an interaction

2 tools

scrape_url_html

scrape_url_markdown

What to know first

Tools you get

Requires

Light Standing cost

Connect your client

Server setup

MCP Clients

Claude Desktop — npx, Any MCP client — stdio

Claude Desktop — Docker

Cursor — stdio, Windsurf — stdio

Cursor — HTTP

Windsurf — HTTP

Kilo Code — npx

Kilo Code — remote

Codex

VS Code

Claude Code — stdio

Claude Code — HTTP

Any MCP client — hosted

Same category

CortexScout Search & Web Extraction

MCP Webscan Server

Apify

ScrapeGraph AI

`scrape_url_html`

`scrape_url_markdown`