# Web Scraper MCP Server

> **Web Scraper MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Web Scraper.
>
> MewCP takes care of all MCP infrastructure for you — credential storage, OAuth flows,
> token refresh, and production-grade auto-scaling — so your AI agents can connect to
> third-party services and run freely without you managing any MCP server yourself.
>
> Server page:  https://mewcp.com/mcp/web-scraper
> MewCP docs:   https://docs.mewcp.com
> All servers:  https://mewcp.com/servers (JSON: https://mewcp.com/api/servers)
> About MewCP:  https://mewcp.com/llms.txt

---

## About

Extract structured data from websites and public web pages. Fetch content, parse information and transform online data into formats that can be consumed by applications, agents and workflows.

---

## Details

- Server ID: `web-scraper`
- Version: 1.0.0
- Tools: 1
- Authentication: None — this server takes no credential
- Calls served: 3381
- Transport: http

---

## Access

The gateway URL below serves your **entire MewCP toolset**, not this server on its
own. Pasting a config snippet is not enough — Web Scraper has to be in the toolset
first. In order:

1. Add Web Scraper to your toolset at https://mewcp.com/mcp/web-scraper
2. Nothing to connect — Web Scraper needs no credential
3. Add the gateway URL to your client (see Connect below). It signs in with OAuth
   the first time it connects, so there is no key to copy.

Once connected, an agent does **not** see this server's tools as top-level tools.
It sees four meta-tools and reaches everything through them:

- `search(query)` — find tools by keyword across the toolset
- `get_schema(tools)` — full description and arguments for the tools you picked
- `list_accounts(provider)` — only when one app has several connected accounts
- `call_tool(server_maskedId, tool_name, args)` — execute

So the list below is what `search` can return for this server, not a set of
callable tool names on their own.

---

## Tools (1)

Descriptions are truncated to 160 characters; call `get_schema`
for the full text and the argument schema. Where a tool is annotated, its type
is shown — treat `destructive` as irreversible.

- `scrape` _(write)_ — Scrape content from a web page given a URL and optional CSS selector.

---

## Connect

- URL: https://gateway.mewcp.com/personal/mcp
- Transport: Streamable HTTP (remote). Nothing to install.
- Sign-in: OAuth. On first connect the client opens a browser window to sign in
  to MewCP and approve access. No API key.
- Headless clients (SDKs, servers without a browser) send an API key instead:
  `Authorization: Bearer <API_KEY>`, key from https://mewcp.com/dashboard/api-keys

Agents setting themselves up: follow https://mewcp.com/SKILL.md

Step-by-step guide per client:

- Claude Desktop: https://mewcp.com/mcp/web-scraper/connect/claude
- ChatGPT: https://mewcp.com/mcp/web-scraper/connect/chatgpt
- VS Code: https://mewcp.com/mcp/web-scraper/connect/vscode
- Cursor: https://mewcp.com/mcp/web-scraper/connect/cursor
- Codex: https://mewcp.com/mcp/web-scraper/connect/codex
- Claude Code: https://mewcp.com/mcp/web-scraper/connect/claude-code
- OpenCode: https://mewcp.com/mcp/web-scraper/connect/opencode
- OpenClaw: https://mewcp.com/mcp/web-scraper/connect/openclaw
- Antigravity: https://mewcp.com/mcp/web-scraper/connect/antigravity
- Hermes: https://mewcp.com/mcp/web-scraper/connect/hermes
- DeepSeek Harness: https://mewcp.com/mcp/web-scraper/connect/dsh
- Python: https://mewcp.com/mcp/web-scraper/connect/python
- TypeScript: https://mewcp.com/mcp/web-scraper/connect/typescript