loading…
Search for a command to run...
loading…
Enables autonomous web automation through Playwright browser control integrated with MolmoWeb's vision model for pixel-level action prediction. Supports end-to-
Enables autonomous web automation through Playwright browser control integrated with MolmoWeb's vision model for pixel-level action prediction. Supports end-to-end task execution via an orchestrator LLM that decomposes natural language instructions into browser actions.
MCP server that exposes MolmoWeb web automation as tools for Claude (or any MCP client). Uses Playwright for browser control.
Claude / MCP Client
↓ stdio (MCP protocol)
molmoweb-mcp (this server)
↓ ↓
Playwright browser MolmoWeb API (localhost:8001)
| Tool | Description |
|---|---|
molmoweb_check_status |
Health check for MolmoWeb backend |
browser_navigate |
Open URL in Playwright browser |
browser_screenshot |
Capture JPEG screenshot (returns base64 image) |
browser_get_page_info |
Get current URL and title |
browser_execute_action |
Execute click/type/scroll/press_key/hover/navigate/wait |
molmoweb_predict |
Ask MolmoWeb vision model what action to perform |
run_web_task |
Full autonomous agent loop (orchestrator + MolmoWeb + execution) |
npm install
npx playwright install chromium
The MolmoWeb vision model must be running at http://127.0.0.1:8001. On Windows with WSL:
# Using the provided script:
run_molmoweb.bat
Add to your ~/.mcp.json (global) or project .mcp.json:
{
"mcpServers": {
"molmoweb": {
"command": "node",
"args": ["/path/to/molmoweb-mcp/server.js"]
}
}
}
npm start
The run_web_task tool uses an LLM orchestrator to decompose tasks into step-by-step browser actions. Supported providers:
MIT
from
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"molmoweb-mcp-server": {
"command": "npx",
"args": []
}
}
}