Simple Web Scraper

Playground

VS Code

Connected to Web Scrapper via MewCP.

Encrypted at rest, isolated from the model

Resolved from an AES-256-GCM vault at the moment of the call and attached to the request — the model never sees the secrets.

Try asking

Everything Web Scrapper can do

Tools1

scrape

write

Scrape content from a web page given a URL and optional CSS selector.

Missing a tool, or found a bug?

Web Scrapper MCP Server is open source. Tell the MewCP maintainers.

Open GitHub Issues

Connect Web Scrapper to your agent

One endpoint, the same key, whichever client you use.

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json (Mac) · %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mewcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://gateway.mewcp.com/personal/mcp",
        "--header",
        "Authorization: Bearer API_KEY"
      ]
    }
  }
}

Replace API_KEY with your own key.

Already have an "mcpServers" section in your config? Just add the server entry inside it.

1. 01Open Claude Desktop → Settings → Developer → "Edit Config"
2. 02Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one)
3. 03Save the file and restart Claude Desktop
4. 04Start a new conversation — your tool will be available

One endpoint. Every service.

Any agent

One Gateway

[

Firecrawl

API Key

](https://mewcp.com/mcp/firecrawl)

[

Context.dev

API Key

](https://mewcp.com/mcp/context-dot-dev)

[

Dice MCP

No auth

](https://mewcp.com/mcp/dice-mcp)

Web Scrapper

No auth

Discovery, routing, credentials, tool scoping and execution logs all happen at the gateway→connections stay ACTIVE with no work from you

Separate connections░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 36 tool definitions ~2.8k tokens With MewCP░░░░░░░░░░░░░░░░░░░░░░░░░░░░ 4 meta-tools ~1.3k tokens

Built for AI agents

Web Scrapper runs through a gateway that holds the credentials, scopes the access and records every call.

Nothing to connect

• Web Scrapper needs no credential, so there is no key to issue, store or rotate.
• Add it to a toolset and start calling tools.

Credentials stay out of context

• Web Scrapper credentials are resolved at the gateway and attached to the outbound call.
• The agent sees tool results, never a token.
• Revoke an account and the next call stops working — no redeploy.

Scoped access, fully logged

• Choose exactly which Web Scrapper tools an agent is allowed to call.
• Every call is logged with its outcome, latency and which account it ran as.
• Catalog changes are reviewed before they ship, so tool descriptions cannot shift under you.

One endpoint for every server

• Reach Web Scrapper through the same MCP endpoint as the rest of your toolset.
• Tools are discovered on demand, so 1 tools do not fill the context window.
• Stateless: no sessions to keep alive and no reconnect logic.