Scrappy Cloud Browser

gg.scrappyPublished by scrappy.ggOfficial publisherv1.16.0Updated Oct 29, 2026

Cloud browsers for AI agents: saved logins, residential IPs, live human takeover, 57 browser tools.

VerifiedStreamable HTTPWeb executableBrowser Automation

Overview

AI-generated overview

Remote MCP endpoint giving AI assistants cloud browsers with saved logins, residential IPs and live human takeover.

What you can do
  • Drive cloud browser sessions from the assistant, using a hosted browser rather than a local one.
  • Reuse saved logins so the assistant can work inside accounts that are already signed in.
  • Route browsing through residential IPs.
  • Hand control of a live session to a human when the assistant gets stuck.
  • Access a large set of browser tools (the provider advertises 57); the individual tool list is not published in the manifest.
When to use it
Useful when an assistant needs to operate real websites that require a signed-in session or a non-datacenter IP, or when a person should be able to step in and finish a task in the same live browser session.
Requirements
A remote MCP endpoint at the provider's host, reached over streamable HTTP. Authentication is a bearer token sent in the Authorization header: a Scrappy API key created in Settings > Developers, with browser:read and browser:write scopes. No local runtime or packages are needed.
Before you install
The API key is a secret sent in the Authorization header and grants read and write browser access; keep it out of logs and shared configs. Saved logins and residential IPs mean the assistant acts inside real accounts and appears as a residential user, so actions it takes there are attributable to those accounts. Human takeover and any usage limits or billing are handled by the provider.

Installation

In SourceWeft

  1. Open Scrappy Cloud Browser in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/gg.scrappy%2Fcloud-browser/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "scrappy-cloud-browser": {
      "type": "http",
      "url": "https://scrappy.gg/api/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

1
  1. v1.16.0LatestOct 29, 2026

Score

56% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Scrappy integrations

PyScrappy

Published by GitHub account mldsveda

PyScrappy is a local MCP server that turns websites into structured, LLM-ready text, links, tables and metadata through 20+ scraping tools.

STDIODesktop only
Web Search & ScrapingNot validated yetOct 24, 2026