Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
async with BrowseSession() as session: # Navigate and get accessibility tree snapshot await session.navigate("https://example.com") snap = await session.snapshot() print(snap.tree_text) # - heading "Example Domain" [level=1] # - link "Learn more": [ref=e1]
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"browsegrab": {
"command": "uvx",
"args": ["browsegrab"],
"env": {
"BROWSEGRAB_LLM_BASE_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| BROWSEGRAB_LLM_BASE_URL | Endpoint or connection string the server talks to. | Yes |
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
An intelligent UI component design selection tool built on the Model Context Protocol (MCP). Allows AI assistants to present multiple UI designs for
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Stdio MCP bridge for the hosted OpenRegistry service
MCP server for 4o-image API integration - Generate images using text prompts and edit existing images