gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP. Gemini画图 MCP和sill，支持龙虾或任何agent使用٩(๑>◡<๑)۶

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), Playwright, Puppeteer or any CDP client.

GenUI for DeepSeek Harness: interactive UI components rendered inline in assistant replies via the dsh-ui fence — layout, charts, plots, forms, quizzes, mermaid, 3D scenes, and an action event loop back to the model. Ships the fence-teaching host plugin, the browser renderer (client half), and the genui skill.

Enables MCP clients to teach on a view-only local browser chalkboard by drawing equations, plots, molecules, diagrams, and science illustrations step by step, with snapshots and saved lessons.

DeepSeek娘 — an unofficial floating desktop companion for the DeepSeek Harness UI. Zero dependencies; sprites inlined as data URIs; schedules on the Client timer service instead of the trapped browser timer globals.

Shared server-side core for MulmoClaude and MulmoTerminal — the always-shipped-together subsystems consolidated behind subpath exports so the two hosts can't drift. Server-only except the browser-safe ./artifacts, ./whisper/client, ./workspace-setup/slug,

Enables AI clients to inspect installed software packages and saved browser traffic through read-only local parsers, producing structured evidence about application structure, dependencies, endpoints, and observed authentication schemes.

Enables MCP clients to review Ceramic and ordinary websites with desktop/mobile browser QA, deterministic design and accessibility checks, optional visual judgement, and repeatable fix verification backed by preserved screenshots and reports.

Enables AI clients to observe foreground browser viewports, read filtered page evidence, and run guarded reusable site-pack procedures through the same local runtime as the CLI.

Enables MCP-capable agent CLIs on macOS to reuse an installed, unmodified OpenAI Browser Runtime to drive a connected Chrome or Edge browser (or a host's in-app browser backend) through js, js_reset, and turn_ended tools. It stays a thin bridge that preserves the Runtime's approval and security boundaries, failing closed when the client cannot handle approval requests.

Enables Claude or any MCP client to use the Google Gemini web app through a real Chrome browser with a normal Google account and no API key, including sending prompts, managing chats, uploading files, downloading results, and inspecting or interacting with pages via accessibility roles.

Enables MCP clients to operate an already-logged-in Chrome tab through a browser extension and chrome.debugger, exposing navigation, page reading, interaction, screenshots, cookies/storage, network and console debugging, downloads, and batch actions under default-deny safety guards.

Bridges a selected browser tab's native WebMCP tools to remote MCP clients through a self-hosted Cloudflare Worker, enabling tool discovery and invocation with session-scoped authentication and per-page trust controls.

Enables MCP clients to look up, save, and update logins and TOTP codes in a running, unlocked KeePassXC database over its browser-integration socket, along with password generation and group management, without ever opening the .kdbx file or handling the master password.

Exposes five read-only tools for checking browser status, searching X posts, searching Xiaohongshu notes, and reading Xiaohongshu notes and comments through a locally installed bb-browser CLI. It targets MCP clients such as Codex, though live retrieval remains unverified.