Where is the source code for Gecko?
The source code is linked from the repository URL on this page.
@Frumane
基本情報
MCP server to drive Firefox-based browsers (Floorp, LibreWolf, Waterfox, Zen, Mullvad, Firefox) from Claude Code, Cursor & any MCP client - read pages, screenshot, automate tabs & forms in your real session. 'Claude in Chrome', but for Gecko.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"gecko": {
"command": "npx",
"args": [
"-y",
"gecko-mcp"
]
}
}
}List all open tabs (title, URL, browserId, active, pinned).
Open a new tab at a URL; **returns the new tab's `browserId`** so you can target it.
Return the active tab's title, URL and browserId.
Navigate an existing tab to a URL.
Close a tab.
Read a tab's content as clean Markdown (or HTML / accessibility tree). Output is capped (default 25 KB) to protect the context.
**Fast element locator** — search a page server-side by visible text and/or tag; returns a compact list of ready-to-use CSS `selector`s (~1 KB) instead of the whole HTML. Use it to find a button/link/field, then act on the selector.
Structured page map: Markdown with inline `fp:` refs + an element selector map — locate elements without grepping HTML, then act via a `ref`.
Capture a screenshot of a tab (viewport or full page).
Ensure Floorp is running — launches it if the API isn't reachable (Windows).
Start any Firefox-based browser (Firefox, LibreWolf, Zen…) with Marionette enabled so gecko-mcp can drive it.
Click an element by CSS selector **or a `ref` from `snapshot`**; auto-scrolls it into view first.
Type into an input/textarea — or a rich/contenteditable editor (Slate, ProseMirror…) — by CSS selector.
Fill multiple fields at once.
Press a keyboard key (Enter, Tab, …).
Wait for an element to attach / become visible / etc.
**Sensitive.** Read the current value of an input/textarea/select (can read password fields).
MCP server to drive Firefox-based browsers (Floorp, LibreWolf, Waterfox, Zen, Mullvad, Firefox) from Claude Code, Cursor & any MCP client - read pages, screenshot, automate tabs & forms in your real session. 'Claude in Chrome', but for Gecko.
The README includes setup instructions such as npx gecko-mcp setup.
The source code is linked from the repository URL on this page.
If the README contains a parseable MCP configuration block, it is shown in the Config tab.
BitBrowser MCP simple to use, no complicated procedures required. Supports a variety of intelligent agent services.
Official Chrome DevTools MCP server from Google that lets coding agents control, debug and profile a live Chrome browser.

Give your AI agent its own proxies. QuantumProxies exposes residential, mobile, datacenter, ISP and IPv6 endpoints as MCP tools: list your plans, generate ready-to-use proxy strings with credentials, target by country, s
Give your AI agent the live web. One MCP server for Search, Fetch, Browser, and Agent: browse real sites, extract structured data, fill forms, and run multi-step workflows. Search and Fetch are free.

Web automation for AI assistants. Ask for a task on a website in plain English and Node Mantis carries it out in a real browser, then hands back the result as structured data.
コメント