Browsegrab MCP Server

Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.

Local serverstdioPython

What is the Browsegrab MCP Server?

Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.

The short version

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]

  • Token-efficient — ~500-1,500 tokens/step (vs 4,000-10,000 for browser-use)
  • Local LLM first — Optimized for vLLM, Ollama, and OpenAI-compatible endpoints
  • MCP native — Built-in MCP server with 8 browser automation tools
  • MarkGrab integration — HTML → clean markdown for content extraction
  • Accessibility tree + ref system — Stable element references (e1, e2, ...) without vision models
  • Success pattern caching — Zero LLM calls on repeated workflows

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the Browsegrab MCP Server

{
  "mcpServers": {
    "browsegrab": {
      "command": "uvx",
      "args": ["browsegrab"],
      "env": {
        "BROWSEGRAB_LLM_BASE_URL": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
BROWSEGRAB_LLM_BASE_URLEndpoint or connection string the server talks to.Yes

Frequently asked questions

Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab. Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.