MCP Tools Directory
← Browse integrations

Browser automation

KitchenSink4Web Community Edition

Free account · sign-in required

Contact KitchenSink4Web Community Edition

Loading secure sign-in…

Tools for autonomous AI agents

About this integration

Runs a local browser MCP server for budgeted page reading, extraction, capture, and optionally user-authorized browser actions.

Transport
stdio
Authentication
unknown
Initial setup
user-authorization
Runtime
unattended
Evidence
documented
Package
kitchensink4web
Last compatibility test
Not independently tested

Connect your agent

kitchensink4web

Publisher README and Python manifest reviewed offline; package and websites were not executed or independently security-audited. It is read-only by default; optional acting, storage, file, diagnostic, and workflow surfaces require deliberate configuration and user confirmation policies.

Capabilities: Read and navigate websites, Extract tables and documents, Optionally click, type, and run browser workflows

Connected profiles

Additional details

Source artifact

kitchensink4web

Source ↗ · Checked 2026-09-19
Source manifest version

1.0.2

Source ↗ · Checked 2026-09-19
Unattended configuration

The publisher documents local uvx execution for Codex CLI and other command-based MCP clients.

Source ↗ · Checked 2026-09-19
Authentication and prerequisites

The MCP server has no single service credential; target-site authentication is represented by user-created browser sessions or saved auth state, with password fields hidden from the server's reading channel.

Source ↗ · Checked 2026-09-19
Connection configuration

Configure a local MCP client to launch uvx kitchensink4web over stdio.

Source ↗ · Checked 2026-09-19
Review scope

Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.

Source ↗ · Checked 2026-09-19