add_bookmark
Add a new bookmark (Extension required)
LABSCO SUMMARY
Your logged-in browser, not a fresh headless one.
What it takes off you is signing in again. The pages the agent reads and fills are the ones already open in your session, and because the calls can be aimed at a background tab, a pass across ten research tabs never takes over the window you are working in.
What it is
A server that drives your existing browser through an extension. Its calls can be aimed at a background tab, so a page can be read, clicked and filled without the tab in front of you changing.
What you get
- Any tab analysed and its content extracted, without switching to it
- Clicks, form fills, scrolling and waits aimed at a background tab, with element state readable before acting
- Tabs created — one, or several at once from a count or a list of URLs — closed, listed with their readiness, and switched between
- Navigation with a wait condition attached
- Browser history searched by keyword, domain, date range and visit count
- Bookmarks read, searched and added
- The page's links returned with internal and external filtering, and the current selection returned as text
- Page appearance changed by theme, colour, font and effect
Requirements
npx on your PATH, and the browser extension installed — every tool is marked as needing it, and the tabs the calls address are the ones open in that browser.
Setup effort
Follow the published steps
USE CASES
01
Reading a set of research tabs at once
The tab list gives the ids, and content or selected text is pulled from each in the background while your own tab stays where it is.
02
Filling a form on a site you are signed in to
The fill runs in your own session with focus and event simulation, so the page behaves as if a person typed into it.
03
Finding the page you had open last week
History is searched by keyword, domain, date range and how often you visited, then the result is opened in a new tab.
04
Opening a batch of pages to work through
A count or a list of URLs opens the whole set in one call, and the tab list hands back the ids needed to work each of them in the background.
05
Collecting the links off a page
Links come back filtered to internal or external, with the page's own content available alongside them.
18 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
element_click
🖱️ BACKGROUND TAB READY: Click elements in any tab without switching! Perform actions on background tabs while staying on current page. Use tab_id to target specific tabs. (Extension required)
element_fill
✏️ BACKGROUND TAB READY: Fill forms in any tab without switching! Enhanced focus and event simulation for modern web apps with anti-detection bypass for Twitter/X, LinkedIn, Facebook. Use tab_id to fill forms in background tabs. (Extension required)
element_get_state
🔍 Get detailed state information for a specific element (disabled, clickable, etc.) (Extension required)
get_bookmarks
Get all bookmarks or search for specific bookmarks (Extension required)
get_history
🕒 Search browser history with comprehensive filters for finding previous work (Extension required)
get_page_links
🔗 Get all hyperlinks on the current page with smart filtering (Extension required)
get_selected_text
📝 BACKGROUND TAB READY: Get selected text from any tab without switching! Perfect for collecting quotes, citations, or highlighted content from multiple research tabs simultaneously. (Extension required)
page_analyze
🔍 BACKGROUND TAB READY: Analyze any tab without switching! Two-phase intelligent page analysis with token efficiency optimization. Use tab_id parameter to analyze background tabs while staying on current page. (Extension required)
page_extract_content
📄 BACKGROUND TAB READY: Extract content from any tab without switching! Perfect for analyzing multiple research tabs, articles, or pages simultaneously. Use tab_id to target specific background tabs. (Extension required)
page_navigate
🧭 Navigate to URLs with wait conditions (Extension required)
page_scroll
📜 BACKGROUND TAB READY: Scroll any tab without switching! Critical for long pages. Navigate through content in background tabs while staying on current page. Use tab_id to target specific tabs. (Extension required)
page_style
🎨 Transform page appearance with themes, colors, fonts, and fun effects! Apply preset themes like 'dark_hacker', 'retro_80s', or create custom styles. Perfect for making boring pages fun or improving readability.
page_wait_for
⏳ Wait for elements or conditions (Extension required)
tab_close
❌ Close specific tab(s) by ID or close current tab (Extension required)
tab_create
Creates tabs. CRITICAL: For multiple identical tabs, ALWAYS use 'count' parameter! Examples: {url: 'https://x.com', count: 5} creates 5 Twitter tabs. {url: 'https://github.com', count: 10} creates 10 GitHub tabs. Single tab: {url: 'https://example.com'}. Multiple different URLs: {urls: ['url1', 'url2']}.
tab_list
📋 TAB DISCOVERY: Get list of all open tabs with IDs for background tab targeting! Shows content script readiness status and tab details. Essential for multi-tab workflows - use tab IDs with other tools to work on background tabs. (Extension required)
tab_switch
🔄 Switch to a specific tab by ID (Extension required)
BEFORE YOU INSTALL
What to know first
Tools you get
18 tools when we connected.
Requires
- npx on PATH
- The OpenDia browser extension, loaded unpacked in Chrome, Chromium or Firefox
Where it runs
All 4 documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 18 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
Download opendia-chrome-1.1.0.zip from https://github.com/aeonfun/opendia/releases/tag/v1.1.0 (for Firefox, opendia-firefox-1.1.0.zip from the same release)
Extract the zip file to a folder
Chrome or Chromium: go to chrome://extensions/, enable "Developer mode", click "Load unpacked" and select the extracted folder. Firefox: go to about:debugging#/runtime/this-firefox, click "Load Temporary Add-on..." and select manifest.json from the extracted folder; Firefox drops it again when it restarts
TERMINAL
npx opendiaMCP Clients
Claude Desktop, Claude Code, Cursor
JSON
{
"mcpServers": {
"opendia": {
"command": "npx",
"args": [
"opendia"
]
}
}
}Grok Build
GROK BUILD · TOML
[mcp_servers.opendia]
command = "npx"
args = ["-y", "opendia"]
enabled = true
startup_timeout_sec = 60
