Free MCP that drives your Chrome and knows how each site works. Say “post this update to LinkedIn” or “manage the products in my online store” and it just runs.
Perfect for users who want to lean back. Essential for busy builders looking for workflow optimization.
85 sites live · MCP free · 3-day trial on every paid Thread
The MCP is what your AI actually uses to do stuff on any website: fill forms, upload files, post updates, click through admin panels, submit orders. It runs on your own Chrome with your own logins, so it acts as you. When a site changes or breaks, it figures it out and keeps working. When one approach fails, it tries a smarter one until the task is done. It reads what it sees on screen when the code alone isn't enough. Free forever, MIT-licensed, open source.
Upwork Profile Editor (hardened)
Google Sign-In Handler
Meta Ads Manager
Google Analytics Ops
app.gumroad.com Starter
bandcamp.com Starter
Free tier is real: MCP + all execution tools + install & run any Thread, forever. Pro tier is for the person who wants to reverse-engineer their own sites: recording, playbook, network capture, drift auto-heal, seed-a- Thread from any tab. Plus Autopilot mode and advanced tools. Cancel any time.
ai_navigate (agent loop), trace_view (hosted debug traces), network_intercept (mock/log XHRs), stealth_pro (fingerprint mask), extract_sdk (RE any site's API).Download webloom-install.md and drag it into your AI agent. It reads the file and runs the install for you. No copy-paste, no manual config.
~/.webloom/ ├── engine/ ← the MCP server ├── threads/ ← your Threads land here │ └── *.thread.json ├── playbook.json ← your learning └── logs/
webloom-install.md
1.2 KB · drag into Claude / Cursor / Continue
Install WebLoom MCP for me.
1. Clone the engine:
git clone https://github.com/webloomhq/engine ~/.webloom/engine
2. Install deps:
cd ~/.webloom/engine && pip install -r requirements.txt
3. Create playbook dirs:
mkdir -p ~/.webloom/threads ~/.webloom/logs
4. Add this to my MCP config (~/.mcp.json under "mcpServers"):
"webloom": {
"type": "stdio",
"command": "python",
"args": ["~/.webloom/engine/server.py"]
}
After that, 62 browser-control tools become available and a local playbook
at ~/.webloom/ fills automatically as I drive websites. Any Threads I drop
in ~/.webloom/threads/ merge into the playbook at runtime.